Xusen Yin, Ralph Weischedel, Jonathan May
We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well when applied to novel task domains. However, the large amount of computation necessary to adequately train and explore the search space of sequential decision making, under a reinforcement learning paradigm, precludes the inclusion of large contextualized language models, which might otherwise enable the desired generalization ability. We introduce a teacher-student imitation learning methodology and a means of converting a reinforcement learning model into a natural language understanding model. Together, these methodologies enable the introduction of contextualized language models into the sequential decision making problem space. We show that models can learn faster and generalize more, leveraging both the imitation learning and the reformulation. Our models exceed teacher performance on various held-out decision problems, by up to 7% on in-domain problems and 24% on out-of-domain problems.
Nada Aldarrab, Jonathan May
Decipherment of historical ciphers is a challenging problem. The language of the target plaintext might be unknown, and ciphertext can have a lot of noise. State-of-the-art decipherment methods use beam search and a neural language model to score candidate plaintext hypotheses for a given cipher, assuming the plaintext language is known. We propose an end-to-end multilingual model for solving simple substitution ciphers. We test our model on synthetic and real historical ciphers and show that our proposed method can decipher text without explicit language identification while still being robust to noise.
Yining Chen, Sorcha Gilroy, Andreas Maletti, Jonathan May, Kevin Knight
We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with softmax, which are commonly used in natural language processing applications. We show that most problems for such RNNs are undecidable, including consistency, equivalence, minimization, and the determination of the highest-weighted string. However, for consistent RNNs the last problem becomes decidable, although the solution length can surpass all computable bounds. If additionally the string is limited to polynomial length, the problem becomes NP-complete and APX-hard. In summary, this shows that approximations and heuristic algorithms are necessary in practical applications of those RNNs.
Hyundong Cho, Shuai Liu, Taiwei Shi, Darpan Jain, Basem Rizk, Yuyang Huang, Zixun Lu, Nuan Wen, Jonathan Gratch, Emilio Ferrara, Jonathan May
Conversational moderation of online communities is crucial to maintaining civility for a constructive environment, but it is challenging to scale and harmful to moderators. The inclusion of sophisticated natural language generation modules as a force multiplier to aid human moderators is a tantalizing prospect, but adequate evaluation approaches have so far been elusive. In this paper, we establish a systematic definition of conversational moderation effectiveness grounded on moderation literature and establish design criteria for conducting realistic yet safe evaluation. We then propose a comprehensive evaluation framework to assess models' moderation capabilities independently of human intervention. With our framework, we conduct the first known study of language models as conversational moderators, finding that appropriately prompted models that incorporate insights from social science can provide specific and fair feedback on toxic behavior but struggle to influence users to increase their levels of respect and cooperation.
Xusen Yin, Jonathan May
Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as task-oriented dialogues or games. However, models that do not have direct access to their state are harder to train; when the only state access is via the medium of language, this can be particularly pronounced. We introduce a new model amenable to deep Q-learning that incorporates a Siamese neural network architecture and a novel refactoring of the Q-value function in order to better represent system state given its approximation over a language channel. We evaluate the model in the context of zero-shot text-based adventure game learning. Extrinsically, our model reaches the baseline's convergence performance point needing only 15% of its iterations, reaches a convergence performance point 15% higher than the baseline's, and is able to play unseen, unrelated games with no fine-tuning. We probe our new model's representation space to determine that intrinsically, this is due to the appropriate clustering of different linguistic mediation into the same state.
Nima Pourdamghani, Nada Aldarrab, Marjan Ghazvininejad, Kevin Knight, Jonathan May
Given a rough, word-by-word gloss of a source language sentence, target language natives can uncover the latent, fully-fluent rendering of the translation. In this work we explore this intuition by breaking translation into a two step process: generating a rough gloss by means of a dictionary and then `translating' the resulting pseudo-translation, or `Translationese' into a fully fluent translation. We build our Translationese decoder once from a mish-mash of parallel data that has the target language in common and then can build dictionaries on demand using unsupervised techniques, resulting in rapidly generated unsupervised neural MT systems for many source languages. We apply this process to 14 test languages, obtaining better or comparable translation results on high-resource languages than previously published unsupervised MT studies, and obtaining good quality results for low-resource languages that have never been used in an unsupervised MT scenario.
Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph Turian
Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle tasks after being trained on text alone, successful linguistic communication relies on a shared experience of the world. It is this shared experience that makes utterances meaningful. Natural language processing is a diverse field, and progress throughout its development has come from new representational theories, modeling techniques, data collection paradigms, and tasks. We posit that the present success of representation learning approaches trained on large, text-only corpora requires the parallel tradition of research on the broader physical and social context of language to address the deeper questions of communication.
Mozhdeh Gheini, Xiang Ren, Jonathan May
We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series of experiments through fine-tuning a translation model on data where either the source or target language has changed. These experiments reveal that fine-tuning only the cross-attention parameters is nearly as effective as fine-tuning all parameters (i.e., the entire translation model). We provide insights into why this is the case and observe that limiting fine-tuning in this manner yields cross-lingually aligned embeddings. The implications of this finding for researchers and practitioners include a mitigation of catastrophic forgetting, the potential for zero-shot translation, and the ability to extend machine translation models to several new language pairs with reduced parameter storage overhead.
Nelson F. Liu, Jonathan May, Michael Pust, Kevin Knight
Most statistical machine translation systems cannot translate words that are unseen in the training data. However, humans can translate many classes of out-of-vocabulary (OOV) words (e.g., novel morphological variants, misspellings, and compounds) without context by using orthographic clues. Following this observation, we describe and evaluate several general methods for OOV translation that use only subword information. We pose the OOV translation problem as a standalone task and intrinsically evaluate our approaches on fourteen typologically diverse languages across varying resource levels. Adding OOV translators to a statistical machine translation system yields consistent BLEU gains (0.5 points on average, and up to 2.0) for all fourteen languages, especially in low-resource scenarios.
Xusen Yin, Jonathan May
In order to train a computer agent to play a text-based computer game, we must represent each hidden state of the game. A Long Short-Term Memory (LSTM) model running over observed texts is a common choice for state construction. However, a normal Deep Q-learning Network (DQN) for such an agent requires millions of steps of training or more to converge. As such, an LSTM-based DQN can take tens of days to finish the training process. Though we can use a Convolutional Neural Network (CNN) as a text-encoder to construct states much faster than the LSTM, doing so without an understanding of the syntactic context of the words being analyzed can slow convergence. In this paper, we use a fast CNN to encode position- and syntax-oriented structures extracted from observed texts as states. We additionally augment the reward signal in a universal and practical manner. Together, we show that our improvements can not only speed up the process by one order of magnitude but also learn a superior agent.
Zihao He, Jonathan May, Kristina Lerman
Detecting norm violations in online communities is critical to maintaining healthy and safe spaces for online discussions. Existing machine learning approaches often struggle to adapt to the diverse rules and interpretations across different communities due to the inherent challenges of fine-tuning models for such context-specific tasks. In this paper, we introduce Context-aware Prompt-based Learning for Norm Violation Detection (CPL-NoViD), a novel method that employs prompt-based learning to detect norm violations across various types of rules. CPL-NoViD outperforms the baseline by incorporating context through natural language prompts and demonstrates improved performance across different rule types. Significantly, it not only excels in cross-rule-type and cross-community norm violation detection but also exhibits adaptability in few-shot learning scenarios. Most notably, it establishes a new state-of-the-art in norm violation detection, surpassing existing benchmarks. Our work highlights the potential of prompt-based learning for context-sensitive norm violation detection and paves the way for future research on more adaptable, context-aware models to better support online community moderators.
Virginia K. Felkner, Ho-Chun Herbert Chang, Eugene Jang, Jonathan May
We present WinoQueer: a benchmark specifically designed to measure whether large language models (LLMs) encode biases that are harmful to the LGBTQ+ community. The benchmark is community-sourced, via application of a novel method that generates a bias benchmark from a community survey. We apply our benchmark to several popular LLMs and find that off-the-shelf models generally do exhibit considerable anti-queer bias. Finally, we show that LLM bias against a marginalized community can be somewhat mitigated by finetuning on data written about or by members of that community, and that social media text written by community members is more effective than news text written about the community by non-members. Our method for community-in-the-loop benchmark development provides a blueprint for future researchers to develop community-driven, harms-grounded LLM benchmarks for other marginalized communities. Note: This version corrects a bug found in evaluation code after publication. General findings have not changed, but tables 5 and 6 and figure 1 have been corrected.
Darshan Deshpande, Shambhavi Sinha, Anirudh Ravi Kumar, Debaditya Pal, Jonathan May
Language Models have previously shown strong negotiation capabilities in closed domains where the negotiation strategy prediction scope is constrained to a specific setup. In this paper, we first show that these models are not generalizable beyond their original training domain despite their wide-scale pretraining. Following this, we propose an automated framework called GNOME, which processes existing human-annotated, closed-domain datasets using Large Language Models and produces synthetic open-domain dialogues for negotiation. GNOME improves the generalizability of negotiation systems while reducing the expensive and subjective task of manual data curation. Through our experimental setup, we create a benchmark comparing encoder and decoder models trained on existing datasets against datasets created through GNOME. Our results show that models trained on our dataset not only perform better than previous state of the art models on domain specific strategy prediction, but also generalize better to previously unseen domains.
Xiyang Zhang, Muhao Chen, Jonathan May
Storytelling, whether via fables, news reports, documentaries, or memoirs, can be thought of as the communication of interesting and related events that, taken together, form a concrete process. It is desirable to extract the event chains that represent such processes. However, this extraction remains a challenging problem. We posit that this is due to the nature of the texts from which chains are discovered. Natural language text interleaves a narrative of concrete, salient events with background information, contextualization, opinion, and other elements that are important for a variety of necessary discourse and pragmatics acts but are not part of the principal chain of events being communicated. We introduce methods for extracting this principal chain from natural language text, by filtering away non-salient events and supportive sentences. We demonstrate the effectiveness of our methods at isolating critical event chains by comparing their effect on downstream tasks. We show that by pre-training large language models on our extracted chains, we obtain improvements in two tasks that benefit from a clear understanding of event chains: narrative prediction and event-based temporal question answering. The demonstrated improvements and ablative studies confirm that our extraction method isolates critical event chains.
Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight
The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we improve baseline NMT models by an average of 5.6 Bleu on four low-resource language pairs. Ensembling and unknown word replacement add another 2 Bleu which brings the NMT performance on low-resource machine translation close to a strong syntax based machine translation (SBMT) system, exceeding its performance on one language pair. Additionally, using the transfer learning model for re-scoring, we can improve the SBMT system by an average of 1.3 Bleu, improving the state-of-the-art on low-resource machine translation.
Dong-Ho Lee, Hyundong Cho, Jonathan May, Jay Pujara
Asking good questions is critical for comprehension and learning, yet evaluating and generating such questions remains a challenging problem. Prior work on inquisitive questions focuses on learner-generated, curiosity-driven queries and evaluates them using indirect metrics, such as salience or information gain, that do not directly capture a question's impact on actual learning outcomes. We introduce QUEST (Question Utility Estimation with Simulated Tests), a framework that uses language models to simulate learners and directly quantify the utility of a question - its contribution to exam performance. QUEST simulates a learner who asks questions and receives answers while studying a textbook chapter, then uses them to take an end-of-chapter exam. Through this simulation, the utility of each question is estimated by its direct effect on exam performance, rather than inferred indirectly based on the underlying content. To support this evaluation, we curate TEXTBOOK-EXAM, a benchmark that aligns textbook sections with end-of-section exam questions across five academic disciplines. Using QUEST, we filter for high-utility questions and fine-tune question generators via rejection sampling. Experiments show that questions generated by QUEST-trained models improve simulated test scores by over 20% compared to strong baselines that are fine-tuned using indirect metrics or leverage prompting methods. Furthermore, utility is only weakly correlated with salience and similarity to exam questions, suggesting that it captures unique signal that benefits downstream performance. QUEST offers a new outcome-driven paradigm for question evaluation and generation - one that moves beyond question-answer content toward measurable improvements in learning outcomes.
Nada Aldarrab, Jonathan May
Deciphering historical substitution ciphers is a challenging problem. Example problems that have been previously studied include detecting cipher type, detecting plaintext language, and acquiring the substitution key for segmented ciphers. However, attacking unsegmented, space-free ciphers is still a challenging task. Segmentation (i.e. finding substitution units) is the first step towards cracking those ciphers. In this work, we propose the first automatic methods to segment those ciphers using Byte Pair Encoding (BPE) and unigram language models. Our methods achieve an average segmentation error of 2\% on 100 randomly-generated monoalphabetic ciphers and 27\% on 3 real homophonic ciphers. We also propose a method for solving non-deterministic ciphers with existing keys using a lattice and a pretrained language model. Our method leads to the full solution of the IA cipher; a real historical cipher that has not been fully solved until this work.
Mozhdeh Gheini, Jonathan May
Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom parent model or at least update an existing parent model's vocabulary for each child language pair they wish to train, in an effort to align parent and child vocabularies. This is not a practical solution. It is wasteful to devote the majority of training time for new language pairs to optimizing parameters on an unrelated data set. Further, this overhead reduces the utility of neural machine translation for deployment in humanitarian assistance scenarios, where extra time to deploy a new language pair can mean the difference between life and death. In this work, we present a `universal' pre-trained neural parent model with constant vocabulary that can be used as a starting point for training practically any new low-resource language to a fixed target language. We demonstrate that our approach, which leverages orthography unification and a broad-coverage approach to subword identification, generalizes well to several languages from a variety of families, and that translation systems built with our approach can be built more quickly than competing methods and with better quality as well.
Hyundong Cho, Jonathan May
Effective dialogue involves grounding, the process of establishing mutual knowledge that is essential for communication between people. Modern dialogue systems are not explicitly trained to build common ground, and therefore overlook this important aspect of communication. Improvisational theater (improv) intrinsically contains a high proportion of dialogue focused on building common ground, and makes use of the yes-and principle, a strong grounding speech act, to establish coherence and an actionable objective reality. We collect a corpus of more than 26,000 yes-and turns, transcribing them from improv dialogues and extracting them from larger, but more sparsely populated movie script dialogue corpora, via a bootstrapped classifier. We fine-tune chit-chat dialogue systems with our corpus to encourage more grounded, relevant conversation and confirm these findings with human evaluations.
Xusen Yin, Jonathan May
We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such games are relatively straightforward for humans to master after a brief exposure to the genre but have been curiously difficult for computer agents to learn. We find that the deep Q-learning strategies that have been successfully leveraged for superhuman performance in single-instance action video games can be applied to learn families of text video games when adopting simple strategies that correlate with human-like learning behavior. Specifically, we build agents that learn to tackle simple scenarios before more complex ones using curriculum learning, that familiarize themselves in an unfamiliar environment by navigating before acting, and that explore uncertain environments more thoroughly using contextual multi-armed bandit decision policies. We demonstrate improved task completion rates over reasonable baselines when evaluating on never-before-seen games of that theme.