Jungo Kasai


pdf bib
ABC: Attention with Bounded-memory Control
Hao Peng | Jungo Kasai | Nikolaos Pappas | Dani Yogatama | Zhaofeng Wu | Lingpeng Kong | Roy Schwartz | Noah Smith
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Transformer architectures have achieved state- of-the-art results on a variety of natural language processing (NLP) tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead prohibitive, especially for long sequences. Attention context can be seen as a random-access memory with each token taking a slot. Under this perspective, the memory size grows linearly with the sequence length, and so does the overhead of reading from it. One way to improve the efficiency is to bound the memory size. We show that disparate approaches can be subsumed into one abstraction, attention with bounded-memory control (ABC), and they vary in their organization of the memory. ABC reveals new, unexplored possibilities. First, it connects several efficient attention variants that would otherwise seem apart. Second, this abstraction gives new insights—an established approach (Wang et al., 2020b) previously thought to not be applicable in causal attention, actually is. Last, we present a new instance of ABC, which draws inspiration from existing ABC approaches, but replaces their heuristic memory-organizing functions with a learned, contextualized one. Our experiments on language modeling, machine translation, and masked language model finetuning show that our approach outperforms previous efficient attention models; compared to the strong transformer baselines, it significantly improves the inference time and space efficiency with no or negligible accuracy loss.


pdf bib
Findings of the 2021 Conference on Machine Translation (WMT21)
Farhad Akhbardeh | Arkady Arkhangorodsky | Magdalena Biesialska | Ondřej Bojar | Rajen Chatterjee | Vishrav Chaudhary | Marta R. Costa-jussa | Cristina España-Bonet | Angela Fan | Christian Federmann | Markus Freitag | Yvette Graham | Roman Grundkiewicz | Barry Haddow | Leonie Harter | Kenneth Heafield | Christopher Homan | Matthias Huck | Kwabena Amponsah-Kaakyire | Jungo Kasai | Daniel Khashabi | Kevin Knight | Tom Kocmi | Philipp Koehn | Nicholas Lourie | Christof Monz | Makoto Morishita | Masaaki Nagata | Ajay Nagesh | Toshiaki Nakazawa | Matteo Negri | Santanu Pal | Allahsera Auguste Tapo | Marco Turchi | Valentin Vydrin | Marcos Zampieri
Proceedings of the Sixth Conference on Machine Translation

This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021.In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories. The taskwas also opened up to additional test suites toprobe specific aspects of translation.

pdf bib
Finetuning Pretrained Transformers into RNNs
Jungo Kasai | Hao Peng | Yizhe Zhang | Dani Yogatama | Gabriel Ilharco | Nikolaos Pappas | Yi Mao | Weizhu Chen | Noah A. Smith
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a signifi- cant computational cost, as the attention mechanism’s complexity scales quadratically with sequence length. Efficient transformer variants have received increasing interest in recent works. Among them, a linear-complexity recurrent variant has proven well suited for autoregressive generation. It approximates the softmax attention with randomized or heuristic feature maps, but can be difficult to train and may yield suboptimal accuracy. This work aims to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy. Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune. With a learned feature map, our approach provides an improved tradeoff between efficiency and accuracy over the standard transformer and other recurrent variants. We also show that the finetuning process has lower training cost relative to training these recurrent variants from scratch. As many models for natural language tasks are increasingly dependent on large-scale pretrained transformers, this work presents a viable approach to improving inference efficiency without repeating the expensive pretraining process.

pdf bib
Probing Across Time: What Does RoBERTa Know and When?
Zeyu Liu | Yizhong Wang | Jungo Kasai | Hannaneh Hajishirzi | Noah A. Smith
Findings of the Association for Computational Linguistics: EMNLP 2021

Models of language trained on very large corpora have been demonstrated useful for natural language processing. As fixed artifacts, they have become the object of intense study, with many researchers “probing” the extent to which they acquire and readily demonstrate linguistic abstractions, factual and commonsense knowledge, and reasoning abilities. Recent work applied several probes to intermediate training stages to observe the developmental process of a large-scale model (Chiang et al., 2020). Following this effort, we systematically answer a question: for various types of knowledge a language model learns, when during (pre)training are they acquired? Using RoBERTa as a case study, we find: linguistic knowledge is acquired fast, stably, and robustly across domains. Facts and commonsense are slower and more domain-sensitive. Reasoning abilities are, in general, not stably acquired. As new datasets, pretraining protocols, and probes emerge, we believe that probing-across-time analyses can help researchers understand the complex, intermingled learning that these models undergo and guide us toward more efficient approaches that accomplish necessary learning faster.

pdf bib
XOR QA: Cross-lingual Open-Retrieval Question Answering
Akari Asai | Jungo Kasai | Jonathan Clark | Kenton Lee | Eunsol Choi | Hannaneh Hajishirzi
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Multilingual question answering tasks typically assume that answers exist in the same language as the question. Yet in practice, many languages face both information scarcity—where languages have few reference articles—and information asymmetry—where questions reference concepts from other cultures. This work extends open-retrieval question answering to a cross-lingual setting enabling questions from one language to be answered via answer content from another language. We construct a large-scale dataset built on 40K information-seeking questions across 7 diverse non-English languages that TyDi QA could not find same-language answers for. Based on this dataset, we introduce a task framework, called Cross-lingual Open-Retrieval Question Answering (XOR QA), that consists of three new tasks involving cross-lingual document retrieval from multilingual and English resources. We establish baselines with state-of-the-art machine translation systems and cross-lingual pretrained models. Experimental results suggest that XOR QA is a challenging task that will facilitate the development of novel techniques for multilingual question answering. Our data and code are available at https://nlp.cs.washington.edu/xorqa/.


pdf bib
Low-Resource Parsing with Crosslingual Contextualized Representations
Phoebe Mulcaire | Jungo Kasai | Noah A. Smith
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language with a large treebank to a language with a small or nonexistent treebank, by sharing parameters between languages in the parser itself. We experiment with a diverse selection of languages in both simulated and truly low-resource scenarios, and show that multilingual CWRs greatly facilitate low-resource dependency parsing even without crosslingual supervision such as dictionaries or parallel text. Furthermore, we examine the non-contextual part of the learned language models (which we call a “decontextual probe”) to demonstrate that polyglot language models better encode crosslingual lexical correspondence compared to aligned monolingual language models. This analysis provides further evidence that polyglot training is an effective approach to crosslingual transfer.

pdf bib
Jabberwocky Parsing: Dependency Parsing with Lexical Noise
Jungo Kasai | Robert Frank
Proceedings of the Society for Computation in Linguistics (SCiL) 2019

pdf bib
Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations
Jeff Da | Jungo Kasai
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing

Pretrained deep contextual representations have advanced the state-of-the-art on various commonsense NLP tasks, but we lack a concrete understanding of the capability of these models. Thus, we investigate and challenge several aspects of BERT’s commonsense representation abilities. First, we probe BERT’s ability to classify various object attributes, demonstrating that BERT shows a strong ability in encoding various commonsense features in its embedding space, but is still deficient in many areas. Next, we show that, by augmenting BERT’s pretraining data with additional data related to the deficient attributes, we are able to improve performance on a downstream commonsense reasoning task while using a minimal amount of data. Finally, we develop a method of fine-tuning knowledge graphs embeddings alongside BERT and show the continued importance of explicit knowledge graphs.

pdf bib
Low-resource Deep Entity Resolution with Transfer and Active Learning
Jungo Kasai | Kun Qian | Sairam Gurajada | Yunyao Li | Lucian Popa
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Entity resolution (ER) is the task of identifying different representations of the same real-world entities across databases. It is a key step for knowledge base creation and text mining. Recent adaptation of deep learning methods for ER mitigates the need for dataset-specific feature engineering by constructing distributed representations of entity records. While these methods achieve state-of-the-art performance over benchmark data, they require large amounts of labeled data, which are typically unavailable in realistic ER applications. In this paper, we develop a deep learning-based method that targets low-resource settings for ER through a novel combination of transfer learning and active learning. We design an architecture that allows us to learn a transferable model from a high-resource setting to a low-resource one. To further adapt to the target dataset, we incorporate active learning that carefully selects a few informative examples to fine-tune the transferred model. Empirical evaluation demonstrates that our method achieves comparable, if not better, performance compared to state-of-the-art learning-based methods while using an order of magnitude fewer labels.

pdf bib
Syntax-aware Neural Semantic Role Labeling with Supertags
Jungo Kasai | Dan Friedman | Robert Frank | Dragomir Radev | Owen Rambow
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We introduce a new syntax-aware model for dependency-based semantic role labeling that outperforms syntax-agnostic models for English and Spanish. We use a BiLSTM to tag the text with supertags extracted from dependency parses, and we feed these supertags, along with words and parts of speech, into a deep highway BiLSTM for semantic role labeling. Our model combines the strengths of earlier models that performed SRL on the basis of a full dependency parse with more recent models that use no syntactic information at all. Our local and non-ensemble model achieves state-of-the-art performance on the CoNLL 09 English and Spanish datasets. SRL models benefit from syntactic information, and we show that supertagging is a simple, powerful, and robust way to incorporate syntax into a neural SRL system.

pdf bib
Polyglot Contextual Representations Improve Crosslingual Transfer
Phoebe Mulcaire | Jungo Kasai | Noah A. Smith
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We introduce Rosita, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages. Our method combines the advantages of contextual word representations with those of multilingual representation learning. We produce language models from dissimilar language pairs (English/Arabic and English/Chinese) and use them in dependency parsing, semantic role labeling, and named entity recognition, with comparisons to monolingual and non-contextual variants. Our results provide further evidence for the benefits of polyglot learning, in which representations are shared across multiple languages.


pdf bib
Robust Multilingual Part-of-Speech Tagging via Adversarial Training
Michihiro Yasunaga | Jungo Kasai | Dragomir Radev
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural language processing. In this paper, we propose and analyze a neural POS tagging model that exploits AT. In our experiments on the Penn Treebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages), we find that AT not only improves the overall tagging accuracy, but also 1) prevents over-fitting well in low resource languages and 2) boosts tagging accuracy for rare / unseen words. We also demonstrate that 3) the improved tagging performance by AT contributes to the downstream task of dependency parsing, and that 4) AT helps the model to learn cleaner word representations. 5) The proposed AT model is generally effective in different sequence labeling tasks. These positive results motivate further use of AT for natural language tasks.

pdf bib
End-to-End Graph-Based TAG Parsing with Neural Networks
Jungo Kasai | Robert Frank | Pauli Xu | William Merrill | Owen Rambow
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Our best end-to-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-the-art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.


pdf bib
TAG Parsing with Neural Networks and Vector Representations of Supertags
Jungo Kasai | Bob Frank | Tom McCoy | Owen Rambow | Alexis Nasr
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unlabeled and labeled attachment scores. The shift-reduce parsing model eschews lexical information entirely, and uses only the 1-best supertags to parse a sentence, providing further support for the claim that supertagging is “almost parsing.” We demonstrate that the embedding vector representations the parser induces for supertags possess linguistically interpretable structure, supporting analogies between grammatical structures like those familiar from recent work in distributional semantics. This dense representation of supertags overcomes the drawbacks for statistical models of TAG as compared to CCG parsing, raising the possibility that TAG is a viable alternative for NLP tasks that require the assignment of richer structural descriptions to sentences.

pdf bib
Linguistically Rich Vector Representations of Supertags for TAG Parsing
Dan Friedman | Jungo Kasai | R. Thomas McCoy | Robert Frank | Forrest Davis | Owen Rambow
Proceedings of the 13th International Workshop on Tree Adjoining Grammars and Related Formalisms

pdf bib
TAG Parser Evaluation using Textual Entailments
Pauli Xu | Robert Frank | Jungo Kasai | Owen Rambow
Proceedings of the 13th International Workshop on Tree Adjoining Grammars and Related Formalisms