Language agents that interact with the world on their own have great potential for automating digital tasks. While large language model (LLM) agents have made progress in understanding and executing tasks such as textual games and webpage control, many real-world tasks also require collaboration with humans or other LLMs in equal roles, which involves intent understanding, task coordination, and communication. To test LLM’s ability to collaborate, we design a blocks-world environment, where two agents, each having unique goals and skills, build a target structure together. To complete the goals, they can act in the world and communicate in natural language. Under this environment, we design increasingly challenging settings to evaluate different collaboration perspectives, from independent to more complex, dependent tasks. We further adopt chain-of-thought prompts that include intermediate reasoning steps to model the partner’s state and identify and correct execution errors. Both human-machine and machine-machine experiments show that LLM agents have strong grounding capacities, and our approach significantly improves the evaluation metric.

The choice of hyperparameters greatly impacts performance in natural language processing. Often, it is hard to tell if a method is better than another or just better tuned. *Tuning curves* fix this ambiguity by accounting for tuning effort. Specifically, they plot validation performance as a function of the number of hyperparameter choices tried so far. While several estimators exist for these curves, it is common to use point estimates, which we show fail silently and give contradictory results when given too little data.Beyond point estimates, *confidence bands* are necessary to rigorously establish the relationship between different approaches. We present the first method to construct valid confidence bands for tuning curves. The bands are exact, simultaneous, and distribution-free, thus they provide a robust basis for comparing methods.Empirical analysis shows that while bootstrap confidence bands, which serve as a baseline, fail to approximate their target confidence, ours achieve it exactly. We validate our design with ablations, analyze the effect of sample size, and provide guidance on comparing models with our method. To promote confident comparisons in future work, we release opda: an easy-to-use library that you can install with pip. https://github.com/nicholaslourie/opda

We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like user response length, sentiment and reaction of the future human utterances in the collected dialogue episodes. Our experiments use the publicly released deployment data from BlenderBot (Xu et al., 2023). Human evaluation indicates improvements in our new models over baseline responses; however, we find that some proxy signals can lead to more generations with undesirable properties as well. For example, optimizing for conversation length can lead to more controversial or unfriendly generations compared to the baseline, whereas optimizing for positive sentiment or reaction can decrease these behaviors.

Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. However, it is unclear where this capability comes from as there is a stark distribution shift between pre-training text and ICL prompts. In this work, we study what patterns of the pre-training data contribute to ICL. We find that LMs’ ICL ability depends on parallel structures in the pre-training data—pairs of phrases following similar templates in the same context window. Specifically, we detect parallel structures by checking whether training on one phrase improves prediction of the other, and conduct ablation experiments to study their effect on ICL. We show that removing parallel structures in the pre-training data reduces LMs’ ICL accuracy by 51% (vs 2% from random ablation). This drop persists even when excluding common patterns such as n-gram repetitions and long-range dependency, showing the diversity and generality of parallel structures. A closer look at the detected parallel structures indicates that they cover diverse linguistic tasks and span long distances in the data.

Large language models such as GPT-3, GPT4, Claude etc., have advanced the state of the art in several natural language generation tasks such as text summarization and machine translation. However when it comes to open-ended tasks with a focus on creativity such as generating stories, poetry, or various forms of figurative language, these state-of-the-art language models are often found to be inadequate. This tutorial aims to bring awareness of the important and emerging research area of open-domain creative generation, with a focus on language generation while also touching on multi-modal generation (e.g., image captioning, visual metaphors). It targets natural language processing (NLP) and artificial intelligence (AI) researchers as well as creative writing practitioners who are interested in building systems that are capable of emulating as well as augmenting human creativity. In particular, we will review recent studies on creative language generation both at the sentence level as well as longer forms of text. We will provide the audiences with a holistic view of 1) the importance and challenges of building creative language generation systems; 2) how we incorporate content planning, domain knowledge and creativity specific heuristics for different forms of creative language generation such as story, poetry, humor, metaphors etc 3) how can we build better evaluation methods for creative text generation? In particular, how could the recent advancement of AI shape the future workforce for creativity? We will conclude the tutorial by outlining future research directions in this area.

Humans tend to follow the Uniform Information Density (UID) principle by distributing information evenly in utterances. We study if decoding algorithms implicitly follow this UID principle, and under what conditions adherence to UID might be desirable for dialogue generation. We generate responses using different decoding algorithms with GPT-2 on the Persona-Chat dataset and collect human judgments on their quality using Amazon Mechanical Turk. We find that (i) surprisingly, model-generated responses follow the UID principle to a greater extent than human responses, and (ii) decoding algorithms that promote UID do not generate higher-quality responses. Instead, when we control for surprisal, non-uniformity of information density correlates with the quality of responses with very low/high surprisal. Our findings indicate that encouraging non-uniform responses is a potential solution to the “likelihood trap” problem (quality degradation in very high-likelihood text). Our dataset containing multiple candidate responses per dialog history along with human-annotated quality ratings is available at: https://huggingface.co/datasets/saranya132/dialog_uid_gpt2.

In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios. We study the sensitivity of ICL with respect to multiple perturbation types. First, we find that label bias obscures the true sensitivity, and therefore prior work may have significantly underestimated ICL sensitivity. Second, we observe a strong negative correlation between ICL sensitivity and accuracy: predictions sensitive to perturbations are less likely to be correct. Motivated by these findings, we propose SenSel, a few-shot selective prediction method that abstains from sensitive predictions. Experiments on ten classification datasets show that SenSel consistently outperforms two commonly used confidence-based and entropy-based baselines on abstention decisions.

Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world applications where noise, such as typographical or grammatical mistakes, is abundant and can result in degraded performance. Unfortunately, works which evaluate the robustness of neural models on noisy data and propose improvements, are limited to the English language. Upon analyzing noise in different languages, we observe that noise types vary greatly across languages. Thus, existing investigations do not generalize trivially to multilingual settings. To benchmark the performance of pretrained multilingual language models, we construct noisy datasets covering five languages and four NLP tasks and observe a clear gap in the performance between clean and noisy data in the zero-shot cross-lingual setting. After investigating several ways to boost the robustness of multilingual models in this setting, we propose Robust Contrastive Pretraining (RCP). RCP combines data augmentation with a contrastive loss term at the pretraining stage and achieves large improvements on noisy (and original test data) across two sentence-level (+3.2%) and two sequence-labeling (+10 F1-score) multilingual classification tasks.

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this framework, we identify three common cases where high rewards are incorrectly assigned to undesirable patterns: noise-induced spurious correlation, naturally occurring spurious correlation, and covariate shift. We show that even though learned metrics achieve high performance on the distribution of the data used to train the reward function, the undesirable patterns may be amplified during RL training of the text generation model. While there has been discussion about reward gaming in the RL or safety community, in this discussion piece, we would like to highlight reward gaming in the natural language generation (NLG) community using concrete conditional text generation examples and discuss potential fixes and areas for future work.

Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values are often estimated with a small number of stochastic model evaluations. However, we show that the estimated Shapley Values are sensitive to random seed choices – the top-ranked features often have little overlap across different seeds, especially on examples with longer input texts. This can only be mitigated by aggregating thousands of model evaluations, which on the other hand, induces substantial computational overheads. To mitigate the trade-off between stability and efficiency, we develop an amortized model that directly predicts each input feature’s Shapley Value without additional model evaluations. It is trained on a set of examples whose Shapley Values are estimated from a large number of model evaluations to ensure stability. Experimental results on two text classification datasets demonstrate that our amortized model estimates Shapley Values accurately with up to 60 times speedup compared to traditional methods. Further, our model does not suffer from stability issues as inference is deterministic. We release our code at https://github.com/yangalan123/Amortized-Interpretability.

In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given a set of underspecified demonstrations in which two features are equally predictive of the labels. First, we characterize the feature biases of GPT-3 models by constructing underspecified demonstrations from a range of NLP datasets and feature combinations. We find that LLMs exhibit clear feature biases—for example, demonstrating a strong bias to predict labels according to sentiment rather than shallow lexical features, like punctuation. Second, we evaluate the effect of different interventions that are designed to impose an inductive bias in favor of a particular feature, such as adding a natural language instruction or using semantically relevant label words. We find that, while many interventions can influence the learner to prefer a particular feature, it can be difficult to overcome strong prior biases. Overall, our results provide a broader picture of the types of features that ICL may be more likely to exploit and how to impose inductive biases that are better aligned with the intended task.

Machine-in-the-loop writing aims to build models that assist humans to accomplish their writing tasks more effectively. Prior work has found that providing users a machine-written draft or sentence-level continuations has limited success since the generated text tends to deviate from users’ intention. To allow the user to retain control over the content, we train a rewriting model that, when prompted, modifies specified spans of text within the user’s original draft to introduce descriptive and figurative elements in the text. We evaluate the model on its ability to collaborate with humans on the task of creative image captioning. On a user study through Amazon Mechanical Turk, our model is rated to be more helpful by users than a baseline infilling language model. In addition, third-party evaluation shows that users write more descriptive and figurative captions when collaborating with our model compared to completing the task alone. However, the improvement is not uniform across user groups: the model is more helpful to skilled users, which risks widening the gap between skilled and novice users, highlighting a need for careful, user-centric evaluation of interactive systems.

Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performance. In this work, we aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning. We find that, on average, increasing the scale of multi-task learning, in terms of the number of tasks, indeed results in better learned representations than smaller multi-task setups. However, if the target tasks are known ahead of time, then training on a smaller set of related tasks is competitive to the large-scale multi-task training at a reduced computational cost.

To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).

Recent work in training large language models (LLMs) to follow natural language instructions has opened up exciting opportunities for natural language interface design. Building on the prior success of large language models in the realm of computer assisted creativity, in this work, we present CoPoet, a collaborative poetry writing system, with the goal of to study if LLM’s actually improve the quality of the generated content. In contrast to auto-completing a user’s text, CoPoet is controlled by user instructions that specify the attributes of the desired text, such as Write a sentence about ‘love’ or Write a sentence ending in ‘fly’. The core component of our system is a language model fine-tuned on a diverse collection of instructions for poetry writing. Our model is not only competitive to publicly available LLMs trained on instructions (InstructGPT), but also capable of satisfying unseen compositional instructions. A study with 15 qualified crowdworkers shows that users successfully write poems with CoPoet on diverse topics ranging from Monarchy to Climate change, which are preferred by third-party evaluators over poems written without the system.

The term ‘spurious correlations’ has been used in NLP to informally denote any undesirable feature-label correlations. However, a correlation can be undesirable because (i) the feature is irrelevant to the label (e.g. punctuation in a review), or (ii) the feature’s effect on the label depends on the context (e.g. negation words in a review), which is ubiquitous in language tasks. In case (i), we want the model to be invariant to the feature, which is neither necessary nor sufficient for prediction. But in case (ii), even an ideal model (e.g. humans) must rely on the feature, since it is necessary (but not sufficient) for prediction. Therefore, a more fine-grained treatment of spurious features is needed to specify the desired model behavior. We formalize this distinction using a causal model and probabilities of necessity and sufficiency, which delineates the causal relations between a feature and a label. We then show that this distinction helps explain results of existing debiasing methods on different spurious features, and demystifies surprising results such as the encoding of spurious features in model representations after debiasing.

Current abstractive summarization systems tend to hallucinate content that is unfaithful to the source document, posing a risk of misinformation. To mitigate hallucination, we must teach the model to distinguish hallucinated summaries from faithful ones. However, the commonly used maximum likelihood training does not disentangle factual errors from other model errors. To address this issue,we propose a back-translation-style approach to augment negative samples that mimic factual errors made by the model. Specifically, we train an elaboration model that generates hallucinated documents given the reference summaries, and then generates negative summaries from the fake documents. We incorporate the negative samples into training through a controlled generator, which produces faithful/unfaithful summaries conditioned on the control codes. Additionally, we find that adding textual entailment data through multitasking further boosts the performance. Experiments on three datasets (XSum, Gigaword, and WikiHow) show that our method consistently improves faithfulness without sacrificing informativeness according to both human and automatic evaluation

The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. Inspired by the recent progress in large language models, we propose in-context tuning (ICT), which recasts task adaptation and prediction as a simple sequence prediction problem: to form the input sequence, we concatenate the task instruction, labeled in-context examples, and the target input to predict; to meta-train the model to learn from in-context examples, we fine-tune a pre-trained language model (LM) to predict the target label given the input sequence on a collection of tasks.We benchmark our method on two collections of text classification tasks: LAMA and BinaryClfs. Compared to MAML which adapts the model through gradient descent, our method leverages the inductive bias of pre-trained LMs to perform pattern matching, and outperforms MAML by an absolute 6% average AUC-ROC score on BinaryClfs, gaining more advantage with increasing model size. Compared to non-fine-tuned in-context learning (i.e. prompting a raw LM), in-context tuning meta-trains the model to learn from in-context examples. On BinaryClfs, ICT improves the average AUC-ROC score by an absolute 10%, and reduces the variance due to example ordering by 6x and example choices by 2x.

Despite recent progress in abstractive summarization, systems still suffer from faithfulness errors. While prior work has proposed models that improve faithfulness, it is unclear whether the improvement comes from an increased level of extractiveness of the model outputs as one naive way to improve faithfulness is to make summarization models more extractive. In this work, we present a framework for evaluating the effective faithfulness of summarization systems, by generating a faithfulness-abstractiveness trade-off curve that serves as a control at different operating points on the abstractiveness spectrum. We then show that the Maximum Likelihood Estimation (MLE) baseline as well as recently proposed methods for improving faithfulness, fail to consistently improve over the control at the same level of abstractiveness. Finally, we learn a selector to identify the most faithful and abstractive summary for a given document, and show that this system can attain higher faithfulness scores in human evaluations while being more abstractive than the baseline system on two datasets. Moreover, we show that our system is able to achieve a better faithfulness-abstractiveness trade-off than the control at the same level of abstractiveness.

While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using counterfactually-augmented data (CAD)—data generated by minimally perturbing examples to flip the ground-truth label—to identify robust features that are invariant under distribution shift. However, empirical results using CAD during training for OOD generalization have been mixed. To explain this discrepancy, through a toy theoretical example and empirical analysis on two crowdsourced CAD datasets, we show that: (a) while features perturbed in CAD are indeed robust features, it may prevent the model from learning unperturbed robust features; and (b) CAD may exacerbate existing spurious correlations in the data. Our results thus show that the lack of perturbation diversity limits CAD’s effectiveness on OOD generalization, calling for innovative crowdsourcing procedures to elicit diverse perturbation of examples.

Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document. We propose new metrics of relevance and redundancy using pointwise mutual information (PMI) between sentences, which can be easily computed by a pre-trained language model. Intuitively, a relevant sentence allows readers to infer the document content (high PMI with the document), and a redundant sentence can be inferred from the summary (high PMI with the summary). We then develop a greedy sentence selection algorithm to maximize relevance and minimize redundancy of extracted sentences. We show that our method outperforms similarity-based methods on datasets in a range of domains including news, medical journal articles, and personal anecdotes.

Despite agreement on the importance of detecting out-of-distribution (OOD) examples, there is little consensus on the formal definition of the distribution shifts of OOD examples and how to best detect them. We categorize these examples as exhibiting a background shift or semantic shift, and find that the two major approaches to OOD detection, calibration and density estimation (language modeling for text), have distinct behavior on these types of OOD data. Across 14 pairs of in-distribution and OOD English natural language understanding datasets, we find that density estimation methods consistently beat calibration methods in background shift settings and perform worse in semantic shift settings. In addition, we find that both methods generally fail to detect examples from challenge data, indicating that these examples constitute a different type of OOD data. Overall, while the categorization we apply explains many of the differences between the two methods, our results call for a more explicit definition of OOD to create better benchmarks and build detectors that can target the type of OOD data expected at test time.

Recent studies show that many NLP systems are sensitive and vulnerable to a small perturbation of inputs and do not generalize well across different datasets. This lack of robustness derails the use of NLP systems in real-world applications. This tutorial aims at bringing awareness of practical concerns about NLP robustness. It targets NLP researchers and practitioners who are interested in building reliable NLP systems. In particular, we will review recent studies on analyzing the weakness of NLP systems when facing adversarial inputs and data with a distribution shift. We will provide the audience with a holistic view of 1) how to use adversarial examples to examine the weakness of NLP models and facilitate debugging; 2) how to enhance the robustness of existing NLP models and defense against adversarial inputs; and 3) how the consideration of robustness affects the real-world NLP applications used in our daily lives. We will conclude the tutorial by outlining future research directions in this area.

Neural abstractive summarization models are prone to generate content inconsistent with the source document, i.e. unfaithful. Existing automatic metrics do not capture such mistakes effectively. We tackle the problem of evaluating faithfulness of a generated summary given its source document. We first collected human annotations of faithfulness for outputs from numerous models on two datasets. We find that current models exhibit a trade-off between abstractiveness and faithfulness: outputs with less word overlap with the source document are more likely to be unfaithful. Next, we propose an automatic question answering (QA) based metric for faithfulness, FEQA, which leverages recent advances in reading comprehension. Given question-answer pairs generated from the summary, a QA model extracts answers from the document; non-matched answers indicate unfaithful information in the summary. Among metrics based on word overlap, embedding similarity, and learned language understanding models, our QA-based metric has significantly higher correlation with human faithfulness scores, especially on highly abstractive summaries.

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of counterexamples where the spurious correlations do not hold. When such minority examples are scarce, pre-trained models perform as poorly as models trained from scratch. In the case of extreme minority, we propose to use multi-task learning (MTL) to improve generalization. Our experiments on natural language inference and paraphrase identification show that MTL with the right auxiliary tasks significantly improves performance on challenging examples without hurting the in-distribution performance. Further, we show that the gain from MTL mainly comes from improved generalization from the minority examples. Our results highlight the importance of data diversity for overcoming spurious correlations.1

Negotiation is a complex activity involving strategic reasoning, persuasion, and psychology. An average person is often far from an expert in negotiation. Our goal is to assist humans to become better negotiators through a machine-in-the-loop approach that combines machine’s advantage at data-driven decision-making and human’s language generation ability. We consider a bargaining scenario where a seller and a buyer negotiate the price of an item for sale through a text-based dialogue. Our negotiation coach monitors messages between them and recommends strategies in real time to the seller to get a better deal (e.g., “reject the proposal and propose a price”, “talk about your personal experience with the product”). The best strategy largely depends on the context (e.g., the current price, the buyer’s attitude). Therefore, we first identify a set of negotiation strategies, then learn to predict the best strategy in a given dialogue context from a set of human-human bargaining dialogues. Evaluation on human-human dialogues shows that our coach increases the profits of the seller by almost 60%.

Deep learning has become the dominant approach to NLP problems, especially when applied on large scale corpora. Recent progress on unsupervised pre-training techniques such as BERT, ELMo, GPT-2, and language modeling in general, when applied on large corpora, is shown to be effective in improving a wide variety of downstream tasks. These techniques push the limits of available hardware, requiring specialized frameworks optimized for GPU, ASIC, and distributed cloud-based training.A few complexities pose challenges to scale these models and algorithms effectively. Compared to other areas where deep learning is applied, these NLP models contain a variety of moving parts: text normalization and tokenization, word representation at subword-level and word-level, variable-length models such as RNN and attention, and sequential decoder based on beam search, among others.In this hands-on tutorial, we take a closer look at the challenges from these complexities and see how with proper tooling with Apache MXNet and GluonNLP, we can overcome these challenges and achieve state-of-the-art results for real-world problems. GluonNLP is a powerful new toolkit that combines MXNet’s speed, the flexibility of Gluon, and an extensive new library automating the most laborious aspects of deep learning for NLP.

Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate contradiction. As exposed by several recent challenge datasets, these models perform poorly when such association is absent, e.g., predicting that “I love dogs.” contradicts “I don’t love cats.”. Our goal is to design learning algorithms that guard against known dataset bias. We formalize the concept of dataset bias under the framework of distribution shift and present a simple debiasing algorithm based on residual fitting, which we call DRiFt. We first learn a biased model that only uses features that are known to relate to dataset bias. Then, we train a debiased model that fits to the residual of the biased model, focusing on examples that cannot be predicted well by biased features only. We use DRiFt to train three high-performing NLI models on two benchmark datasets, SNLI and MNLI. Our debiased models achieve significant gains over baseline models on two challenge test sets, while maintaining reasonable performance on the original test sets.

We tackle the problem of generating a pun sentence given a pair of homophones (e.g., “died” and “dyed”). Puns are by their very nature statistically anomalous and not amenable to most text generation methods that are supervised by a large corpus. In this paper, we propose an unsupervised approach to pun generation based on lots of raw (unhumorous) text and a surprisal principle. Specifically, we posit that in a pun sentence, there is a strong association between the pun word (e.g., “dyed”) and the distant context, but a strong association between the alternative word (e.g., “died”) and the immediate context. We instantiate the surprisal principle in two ways: (i) as a measure based on the ratio of probabilities given by a language model, and (ii) a retrieve-and-edit approach based on words suggested by a skip-gram model. Based on human evaluation, our retrieve-and-edit approach generates puns successfully 30% of the time, doubling the success rate of a neural generation baseline.

We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., “screen is just the right size” to “screen is too small”). Our training data includes only sentences labeled with their attribute (e.g., positive and negative), but not pairs of sentences that only differ in the attributes, so we must learn to disentangle attributes from attribute-independent content in an unsupervised way. Previous work using adversarial methods has struggled to produce high-quality outputs. In this paper, we propose simpler methods motivated by the observation that text attributes are often marked by distinctive phrases (e.g., “too small”). Our strongest method extracts content words by deleting phrases associated with the sentence’s original attribute value, retrieves new phrases associated with the target attribute, and uses a neural model to fluently combine these into a final output. Based on human evaluation, our best method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets: altering sentiment of reviews on Yelp, altering sentiment of reviews on Amazon, and altering image captions to be more romantic or humorous.

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts from the text. QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as we show in a detailed qualitative evaluation. We also report results for a number of reference models, including a recently state-of-the-art reading comprehension architecture extended to model dialog context. Our best model underperforms humans by 20 F1, suggesting that there is significant room for future work on this data. Dataset, baseline, and leaderboard available at http://quac.ai.

We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing $50) and the execution of that strategy (e.g., generating “The bike is brand new. Selling for just $50!”). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse dialogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.

We know very little about how neural language models (LM) use prior linguistic context. In this paper, we investigate the role of context in an LSTM LM, through ablation studies. Specifically, we analyze the increase in perplexity when prior context words are shuffled, replaced, or dropped. On two standard datasets, Penn Treebank and WikiText-2, we find that the model is capable of using about 200 tokens of context on average, but sharply distinguishes nearby context (recent 50 tokens) from the distant history. The model is highly sensitive to the order of words within the most recent sentence, but ignores word order in the long-range context (beyond 50 tokens), suggesting the distant past is modeled only as a rough semantic field or topic. We further find that the neural caching model (Grave et al., 2017b) especially helps the LSTM to copy words from within this distant context. Overall, our analysis not only provides a better understanding of how neural LMs use their context, but also sheds light on recent success from cache-based models.

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.