Building natural language inference (NLI) benchmarks that are both challenging for modern techniques, and free from shortcut biases is difficult. Chief among these biases is “single sentence label leakage,” where annotator-introduced spurious correlations yield datasets where the logical relation between (premise, hypothesis) pairs can be accurately predicted from only a single sentence, something that should in principle be impossible. We demonstrate that despite efforts to reduce this leakage, it persists in modern datasets that have been introduced since its 2018 discovery. To enable future amelioration efforts, introduce a novel model-driven technique, the progressive evaluation of cluster outliers (PECO) which enables both the objective measurement of leakage, and the automated detection of subpopulations in the data which maximally exhibit it.

Trustworthy answer content is abundant in many high-resource languages and is instantly accessible through question answering systems — yet this content can be hard to access for those that do not speak these languages. The leap forward in cross-lingual modeling quality offered by generative language models offers much promise, yet their raw generations often fall short in factuality. To improve trustworthiness in these systems, a promising direction is to attribute the answer to a retrieved source, possibly in a content-rich language different from the query. Our work is the first to study attribution for cross-lingual question answering. First, we collect data in 5 languages to assess the attribution level of a state-of-the-art cross-lingual QA system. To our surprise, we find that a substantial portion of the answers is not attributable to any retrieved passages (up to 50% of answers exactly matching a gold reference) despite the system being able to attend directly to the retrieved text. Second, to address this poor attribution level, we experiment with a wide range of attribution detection techniques. We find that Natural Language Inference models and PaLM 2 fine-tuned on a very small amount of attribution data can accurately detect attribution. With these models, we improve the attribution level of a cross-lingual QA system. Overall, we show that current academic generative cross-lingual QA systems have substantial shortcomings in attribution and we build tooling to mitigate these issues.

The recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy. However, their capabilities to solve more challenging math problems which require domain-specific knowledge (i.e. theorem) have yet to be investigated. In this paper, we introduce TheoremQA, the first theorem-driven question-answering dataset designed to evaluate AI models’ capabilities to apply theorems to solve challenging science problems. TheoremQA is curated by domain experts containing 800 high-quality questions covering 350 theorems from Math, Physics, EE&CS, and Finance. We evaluate a wide spectrum of 16 large language and code models with different prompting strategies like Chain-of-Thoughts and Program-of-Thoughts. We found that GPT-4’s capabilities to solve these problems are unparalleled, achieving an accuracy of 51% with Program-of-Thoughts Prompting. All the existing open-sourced models are below 15%, barely surpassing the random-guess baseline. Given the diversity and broad coverage of TheoremQA, we believe it can be used as a better benchmark to evaluate LLMs’ capabilities to solve challenging science problems.

The field of text-to-image (T2I) generation has garnered significant attention both within the research community and among everyday users. Despite the advancements of T2I models, a common issue encountered by users is the need for repetitive editing of input prompts in order to receive a satisfactory image, which is time-consuming and labor-intensive. Given the demonstrated text generation power of large-scale language models, such as GPT-k, we investigate the potential of utilizing such models to improve the prompt editing process for T2I generation. We conduct a series of experiments to compare the common edits made by humans and GPT-k, evaluate the performance of GPT-k in prompting T2I, and examine factors that may influence this process. We found that GPT-k models focus more on inserting modifiers while humans tend to replace words and phrases, which includes changes to the subject matter. Experimental results show that GPT-k are more effective in adjusting modifiers rather than predicting spontaneous changes in the primary subject matters. Adopting the edit suggested by GPT-k models may reduce the percentage of remaining edits by 20-30%.

We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting. We observe that the semantic confusion on event types stems from the annotations of the same text being updated over time. The imbalance between event types even aggravates this issue. This paper proposes a novel continual event extraction model with semantic confusion rectification. We mark pseudo labels for each sentence to alleviate semantic confusion. We transfer pivotal knowledge between current and previous models to enhance the understanding of event types. Moreover, we encourage the model to focus on the semantics of long-tailed event types by leveraging other associated types. Experimental results show that our model outperforms state-of-the-art baselines and is proficient in imbalanced datasets.

Recent works on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead compared to subword-based alternatives. However, previous work mainly focuses on reporting accuracy on a limited set of tasks and data settings, placing less emphasis on other important factors when tuning and deploying the models in practice, such as memory usage, inference speed, and finetuning data efficiency. We attempt to fill this gap by performing a comprehensive empirical comparison of multilingual tokenizer-free and subword-based models considering the various dimensions. Surprisingly, we find that subword-based models might still be the most practical choice in many settings, achieving better performance for lower inference latency and memory usage. Based on these results, we encourage future work in tokenizer-free methods to consider these factors when designing and evaluating new models.

Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity. In this paper, we propose a new model, namely SCKD, to accomplish the continual few-shot RE task. Specifically, we design serial knowledge distillation to preserve the prior knowledge from previous models and conduct contrastive learning with pseudo samples to keep the representations of samples in different relations sufficiently distinguishable. Our experiments on two benchmark datasets validate the effectiveness of SCKD for continual few-shot RE and its superiority in knowledge transfer and memory utilization over state-of-the-art models.

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) — languages for which NLP research is particularly far behind in meeting user needs — it is feasible to annotate small amounts of data. Motivated by this, we propose XTREME-UP, a benchmark defined by: its focus on the scarce-data scenario rather than zero-shot; its focus on user-centric tasks — tasks with broad adoption by speakers of high-resource languages; and its focus on under-represented languages where this scarce-data scenario tends to be most realistic. XTREME-UP evaluates the capabilities of language models across 88 under-represented languages over 9 key user-centric technologies including ASR, OCR, MT, and information access tasks that are of general utility. We create new datasets for OCR, autocomplete, semantic parsing, and transliteration, and build on and refine existing datasets for other tasks. XTREME-UP provides methodology for evaluating many modeling scenarios including text only, multi-modal (vision, audio, and text), supervised parameter tuning, and in-context learning. We evaluate commonly used models on the benchmark. We release all code and scripts to train and evaluate models.

Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings. To address these challenges, we propose mmT5, a modular multilingual sequence-to-sequence model. mmT5 utilizes language-specific modules during pre-training, which disentangle language-specific information from language-agnostic information. We identify representation drift during fine-tuning as a key limitation of modular generative models and develop strategies that enable effective zero-shot transfer. Our model outperforms mT5 at the same parameter sizes by a large margin on representative natural language understanding and generation tasks in 40+ languages. Compared to mT5, mmT5 raises the rate of generating text in the correct language under zero-shot settings from 7% to 99%, thereby greatly alleviating the source language hallucination problem.

Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which integrates LLMs with symbolic solvers to improve logical problem-solving. Our method first utilizes LLMs to translate a natural language problem into a symbolic formulation. Afterward, a deterministic symbolic solver performs inference on the formulated problem. We also introduce a self-refinement module, which utilizes the symbolic solver’s error messages to revise symbolic formalizations. We demonstrate Logic-LM’s effectiveness on five logical reasoning datasets: ProofWriter, PrOntoQA, FOLIO, LogicalDeduction, and AR-LSAT. On average, Logic-LM achieves a significant performance boost of 39.2% over using LLM alone with standard prompting and 18.4% over LLM with chain-of-thought prompting. Our findings suggest that Logic-LM, by combining LLMs with symbolic logic, offers a promising avenue for faithful logical reasoning.

This paper describes CMU’s submissions to the IWSLT 2022 dialect speech translation (ST) shared task for translating Tunisian-Arabic speech to English text. We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems. We also augment the paired ASR data with pseudo translations via sequence-level knowledge distillation from an MT model and use these artificial triplet ST data to improve our end-to-end (E2E) systems. Our E2E models are based on the Multi-Decoder architecture with searchable hidden intermediates. We extend the Multi-Decoder by orienting the speech encoder towards the target language by applying ST supervision as hierarchical connectionist temporal classification (CTC) multi-task. During inference, we apply joint decoding of the ST CTC and ST autoregressive decoder branches of our modified Multi-Decoder. Finally, we apply ROVER voting, posterior combination, and minimum bayes-risk decoding with combined N-best lists to ensemble our various cascaded and E2E systems. Our best systems reached 20.8 and 19.5 BLEU on test2 (blind) and test1 respectively. Without any additional MSA data, we reached 20.4 and 19.2 on the same test sets.

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world’s languages cannot benefit from recent progress in NLP as they have no or limited textual data. To expand possibilities of using NLP technology in these under-represented languages, we systematically study strategies that relax the reliance on conventional language resources through the use of bilingual lexicons, an alternative resource with much better language coverage. We analyze different strategies to synthesize textual or labeled data using lexicons, and how this data can be combined with monolingual or parallel text when available. For 19 under-represented languages across 3 tasks, our methods lead to consistent improvements of up to 5 and 15 points with and without extra monolingual text respectively. Overall, our study highlights how NLP methods can be adapted to thousands more languages that are under-served by current technology.

Broader disclosive transparency—truth and clarity in communication regarding the function of AI systems—is widely considered desirable. Unfortunately, it is a nebulous concept, difficult to both define and quantify. This is problematic, as previous work has demonstrated possible trade-offs and negative consequences to disclosive transparency, such as a confusion effect, where “too much information” clouds a reader’s understanding of what a system description means. Disclosive transparency’s subjective nature has rendered deep study into these problems and their remedies difficult. To improve this state of affairs, We introduce neural language model-based probabilistic metrics to directly model disclosive transparency, and demonstrate that they correlate with user and expert opinions of system transparency, making them a valid objective proxy. Finally, we demonstrate the use of these metrics in a pilot study quantifying the relationships between transparency, confusion, and user perceptions in a corpus of real NLP system descriptions.

Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models (Pfeiffer et al., 2020b). However, this approach requires training a separate language adapter for every language one wishes to support, which can be impractical for languages with limited data. An intuitive solution is to use a related language adapter for the new language variety, but we observe that this solution can lead to sub-optimal performance. In this paper, we aim to improve the robustness of language adapters to uncovered languages without training new adapters. We find that ensembling multiple existing language adapters makes the fine-tuned model significantly more robust to other language varieties not included in these adapters. Building upon this observation, we propose Entropy Minimized Ensemble of Adapters (EMEA), a method that optimizes the ensemble weights of the pretrained language adapters for each test sentence by minimizing the entropy of its predictions. Experiments on three diverse groups of language varieties show that our method leads to significant improvements on both named entity recognition and part-of-speech tagging across all languages.

Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary. However, standard heuristic algorithms often lead to sub-optimal segmentation, especially for languages with limited amounts of data. In this paper, we take two major steps towards alleviating this problem. First, we demonstrate empirically that applying existing subword regularization methods (Kudo, 2018; Provilkov et al., 2020) during fine-tuning of pre-trained multilingual representations improves the effectiveness of cross-lingual transfer. Second, to take full advantage of different possible input segmentations, we propose Multi-view Subword Regularization (MVR), a method that enforces the consistency of predictors between using inputs tokenized by the standard and probabilistic segmentations. Results on the XTREME multilingual benchmark (Hu et al., 2020) show that MVR brings consistent improvements of up to 2.5 points over using standard segmentation algorithms.

When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample less resourced languages to increase representation, and the degree of up-sampling has a large effect on the overall performance. In this paper, we propose a method that instead automatically learns how to weight training data through a data scorer that is optimized to maximize performance on all test languages. Experiments on two sets of languages under both one-to-many and many-to-one MT settings show our method not only consistently outperforms heuristic baselines in terms of average performance, but also offers flexible control over the performance of which languages are optimized.

To improve the performance of Neural Machine Translation (NMT) for low-resource languages (LRL), one effective strategy is to leverage parallel data from a related high-resource language (HRL). However, multilingual data has been found more beneficial for NMT models that translate from the LRL to a target language than the ones that translate into the LRLs. In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate into the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft Decoupled Encoding (Wang et al., 2019), we propose DecSDE, an efficient character n-gram based embedding specifically designed for the NMT decoder. Our experiments show that DecSDE leads to consistent gains of up to 1.8 BLEU on translation from English to four different languages.

To improve low-resource Neural Machine Translation (NMT) with multilingual corpus, training on the most related high-resource language only is generally more effective than us- ing all data available (Neubig and Hu, 2018). However, it remains a question whether a smart data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose and efficient algorithm, (TCS), which first samples a target sentence, and then conditionally samples its source sentence. Experiments show TCS brings significant gains of up to 2 BLEU improvements on three of four languages we test, with minimal training overhead.

In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the results of systems for language generation tasks such as machine translation. The main goal of the tool is to give the user a high-level and coherent view of the salient differences between systems that can then be used to guide further analysis or system improvement. It implements a number of tools to do so, such as analysis of accuracy of generation of particular types of words, bucketed histograms of sentence accuracies or counts based on salient characteristics, and extraction of characteristic n-grams for each system. It also has a number of advanced features such as use of linguistic labels, source side data, or comparison of log likelihoods for probabilistic models, and also aims to be easily extensible by users to new types of analysis. compare-mt is a pure-Python open source package, that has already proven useful to generate analyses that have been used in our published papers. Demo Video: https://youtu.be/NyJEQT7t2CA

Neural networks are known to be data hungry and domain sensitive, but it is nearly impossible to obtain large quantities of labeled data for every domain we are interested in. This necessitates the use of domain adaptation strategies. One common strategy encourages generalization by aligning the global distribution statistics between source and target domains, but one drawback is that the statistics of different domains or tasks are inherently divergent, and smoothing over these differences can lead to sub-optimal performance. In this paper, we propose the framework of Domain Differential Adaptation (DDA), where instead of smoothing over these differences we embrace them, directly modeling the difference between domains using models in a related task. We then use these learned domain differentials to adapt models for the target task accordingly. Experimental results on domain adaptation for neural machine translation demonstrate the effectiveness of this strategy, achieving consistent improvements over other alternative adaptation strategies in multiple experimental settings.

In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three translation datasets of different scales show that SwitchOut yields consistent improvements of about 0.5 BLEU, achieving better or comparable performances to strong alternatives such as word dropout (Sennrich et al., 2016a). Code to implement this method is included in the appendix.

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU.