papers

Publications (36)

cs.CL2022

Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection

Jianguo Zhang, Kazuma Hashimoto, Yao Wan +4

Pre-trained Transformer-based models were reported to be robust in intent classification. In this work, we first point out the importance of in-domain out-of-scope detection in few…

cs.IR2021

Dense Hierarchical Retrieval for Open-Domain Question Answering

Ye Liu, Kazuma Hashimoto, Yingbo Zhou +3

Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum…

cs.IR2020

CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization

Andre Esteva, Anuprit Kale, Romain Paulus +4

The COVID-19 global pandemic has resulted in international efforts to understand, track, and mitigate the disease, yielding a significant corpus of COVID-19 and SARS-CoV-2-related…

cs.CL2022

OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval

Tong Niu, Kazuma Hashimoto, Yingbo Zhou +1

Aligning parallel sentences in multilingual corpora is essential to curating data for downstream applications such as Machine Translation. In this work, we present OneAligner, an a…

cs.CL2018

Multilingual Extractive Reading Comprehension by Runtime Machine Translation

Akari Asai, Akiko Eriguchi, Kazuma Hashimoto +1

Despite recent work in Reading Comprehension (RC), progress has been mostly limited to English due to the lack of large-scale datasets in other languages. In this work, we introduc…

cs.CL2016

Tree-to-Sequence Attentional Neural Machine Translation

Akiko Eriguchi, Kazuma Hashimoto, Yoshimasa Tsuruoka

Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information. We propose a novel end-to-end…

cs.CL2021

Focused Attention Improves Document-Grounded Generation

Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou +2

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation…

cs.CL2016

Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings

Kazuma Hashimoto, Yoshimasa Tsuruoka

We present a novel method for jointly learning compositional and non-compositional phrase embeddings by adaptively weighting both types of embeddings using a compositionality scori…

cs.IR2023

Exploring the Viability of Synthetic Query Generation for Relevance Prediction

Aditi Chaudhary, Karthik Raman, Krishna Srinivasan +3

Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models w…

cs.CL2017

Neural Machine Translation with Source-Side Latent Graph Parsing

Kazuma Hashimoto, Yoshimasa Tsuruoka

This paper presents a novel neural machine translation model which jointly learns translation and source-side latent graph representations of sentences. Unlike existing pipelined a…

cs.CL2024

Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning

Kazuma Hashimoto, Karthik Raman, Michael Bendersky

In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs). Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies ha…

cs.CL2020

Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking

Jian-Guo Zhang, Kazuma Hashimoto, Chien-Sheng Wu +4

Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and onto…

cs.CV2022

Field Extraction from Forms with Unlabeled Data

Mingfei Gao, Zeyuan Chen, Nikhil Naik +3

We propose a novel framework to conduct field extraction from forms with unlabeled data. To bootstrap the training process, we develop a rule-based method for mining noisy pseudo-l…

cs.CL2025

Refract ICL: Rethinking Example Selection in the Era of Million-Token Models

Arjun R. Akula, Kazuma Hashimoto, Krishna Srinivasan +3

The emergence of long-context large language models (LLMs) has enabled the use of hundreds, or even thousands, of demonstrations for in-context learning (ICL) - a previously imprac…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2016

Domain Adaptation for Neural Networks by Parameter Augmentation

Yusuke Watanabe, Kazuma Hashimoto, Yoshimasa Tsuruoka

We propose a simple domain adaptation method for neural networks in a supervised setting. Supervised domain adaptation is a way of improving the generalization performance on the t…

cs.CL2022

RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering

Xi Ye, Semih Yavuz, Kazuma Hashimoto +2

Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-base…

cs.CL2020

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi +2

Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationshi…

cs.CL2017

A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks

Kazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka +1

Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax a…

cs.CL2022

Transforming Sequence Tagging Into A Seq2Seq Task

Karthik Raman, Iftekhar Naim, Jiecao Chen +3

Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a…

cs.CL2020

Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT

Lichao Sun, Kazuma Hashimoto, Wenpeng Yin +4

There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, ho…

cs.CL2024

How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling?

Kazuma Hashimoto, Iftekhar Naim, Karthik Raman

Sequence labeling is a core task in text understanding for IE/IR systems. Text generation models have increasingly become the go-to solution for such tasks (e.g., entity extraction…

cs.CL2019

Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction

Kazuma Hashimoto, Yoshimasa Tsuruoka

A major obstacle in reinforcement learning-based sentence generation is the large action space whose size is equal to the vocabulary size of the target-side language. To improve th…

cs.CL2015

Task-Oriented Learning of Word Embeddings for Semantic Relation Classification

Kazuma Hashimoto, Pontus Stenetorp, Makoto Miwa +1

We present a novel learning method for word embeddings designed for relation classification. Our word embeddings are trained by predicting words between noun pairs using lexical re…

cs.CL2021

Causal-aware Safe Policy Improvement for Task-oriented dialogue

Govardana Sachithanandam Ramachandran, Kazuma Hashimoto, Caiming Xiong

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been traine…

cs.CL2022

Modeling Multi-hop Question Answering as Single Sequence Prediction

Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou +2

Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state…

cs.CL2021

CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers

Shiyang Li, Semih Yavuz, Kazuma Hashimoto +6

Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations…

cs.CL2022

GROOT: Corrective Reward Optimization for Generative Sequential Labeling

Kazuma Hashimoto, Karthik Raman

Sequential labeling is a fundamental NLP task, forming the backbone of many applications. Supervised learning of Seq2Seq models has shown great success on these problems. However,…

cs.CL2022

Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering

Man Luo, Kazuma Hashimoto, Semih Yavuz +3

While both extractive and generative readers have been successfully applied to the Question Answering (QA) task, little attention has been paid toward the systematic comparison of…

cs.CL2020

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

Jian-Guo Zhang, Kazuma Hashimoto, Wenhao Liu +5

Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is…

cs.CL2022

Converse: A Tree-Based Modular Task-Oriented Dialogue System

Tian Xie, Xinyi Yang, Angela S. Lin +13

Creating a system that can have meaningful conversations with humans to help accomplish tasks is one of the ultimate goals of Artificial Intelligence (AI). It has defined the meani…

cs.SE2026

PyMETA: A Benchmark Dataset for Hierarchical Student Code Error Classification with Python-Interpreter-Based Labels

Chuyue Li, Ziqi Tang, Jingyi Wang +3

With the advancement of Large Language Models (LLMs), code error detection has extended beyond traditional IDE diagnostics to context-sensitive debugging in educational scenarios.…

cs.CL2020

A High-Quality Multilingual Dataset for Structured Documentation Translation

Kazuma Hashimoto, Raffaella Buschiazzo, James Bradbury +3

This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for transla…

cs.CL2022

Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control

Haopeng Zhang, Semih Yavuz, Wojciech Kryscinski +2

Abstractive summarization systems leveraging pre-training language models have achieved superior results on benchmark datasets. However, such models have been shown to be more pron…

cs.CL2020

Neural Text Generation with Artificial Negative Examples

Keisuke Shirai, Kazuma Hashimoto, Akiko Eriguchi +2

Neural text generation models conditioning on given input (e.g. machine translation and image captioning) are usually trained by maximum likelihood estimation of target text. Howev…

cs.CL2024

Ambiguity-Aware In-Context Learning with Large Language Models

Lingyu Gao, Aditi Chaudhary, Krishna Srinivasan +3

In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensit…