Kai Zhao


2023

pdf bib
Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning
Yougang Lyu | Jitai Hao | Zihan Wang | Kai Zhao | Shen Gao | Pengjie Ren | Zhumin Chen | Fang Wang | Zhaochun Ren
Findings of the Association for Computational Linguistics: EMNLP 2023

Multiple defendants in a criminal fact description generally exhibit complex interactions, and cannot be well handled by existing Legal Judgment Prediction (LJP) methods which focus on predicting judgment results (e.g., law articles, charges, and terms of penalty) for single-defendant cases. To address this problem, we propose the task of multi-defendant LJP, which aims to automatically predict the judgment results for each defendant of multi-defendant cases. Two challenges arise with the task of multi-defendant LJP: (1) indistinguishable judgment results among various defendants; and (2) the lack of a real-world dataset for training and evaluation. To tackle the first challenge, we formalize the multi-defendant judgment process as hierarchical reasoning chains and introduce a multi-defendant LJP method, named Hierarchical Reasoning Network (HRN), which follows the hierarchical reasoning chains to determine criminal relationships, sentencing circumstances, law articles, charges, and terms of penalty for each defendant. To tackle the second challenge, we collect a real-world multi-defendant LJP dataset, namely MultiLJP, to accelerate the relevant research in the future. Extensive experiments on MultiLJP verify the effectiveness of our proposed HRN.

2017

pdf bib
OSU Multimodal Machine Translation System Report
Mingbo Ma | Dapeng Li | Kai Zhao | Liang Huang
Proceedings of the Second Conference on Machine Translation

pdf bib
Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank
Kai Zhao | Liang Huang
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing. Most attempts at this problem rely on annotated text segmentations (Elementary Discourse Units, EDUs) and sophisticated sparse or continuous features to extract syntactic information. In this paper we propose the first end-to-end discourse parser that jointly parses in both syntax and discourse levels, as well as the first syntacto-discourse treebank by integrating the Penn Treebank and the RST Treebank. Built upon our recent span-based constituency parser, this joint syntacto-discourse parser requires no preprocessing efforts such as segmentation or feature extraction, making discourse parsing more convenient. Empirically, our parser achieves the state-of-the-art end-to-end discourse parsing accuracy.

pdf bib
When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)
Liang Huang | Kai Zhao | Mingbo Ma
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality. However, in the neural generation setting, hypotheses can finish in different steps, which makes it difficult to decide when to end beam search to ensure optimality. We propose a provably optimal beam search algorithm that will always return the optimal-score complete hypothesis (modulo beam size), and finish as soon as the optimality is established. To counter neural generation’s tendency for shorter hypotheses, we also introduce a bounded length reward mechanism which allows a modified version of our beam search algorithm to remain optimal. Experiments on neural machine translation demonstrate that our principled beam search algorithm leads to improvement in BLEU score over previously proposed alternatives.

2016

pdf bib
Textual Entailment with Structured Attentions and Composition
Kai Zhao | Liang Huang | Mingbo Ma
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Deep learning techniques are increasingly popular in the textual entailment task, overcoming the fragility of traditional discrete models with hard alignments and logics. In particular, the recently proposed attention models (Rocktäschel et al., 2015; Wang and Jiang, 2015) achieves state-of-the-art accuracy by computing soft word alignments between the premise and hypothesis sentences. However, there remains a major limitation: this line of work completely ignores syntax and recursion, which is helpful in many traditional efforts. We show that it is beneficial to extend the attention model to tree nodes between premise and hypothesis. More importantly, this subtree-level attention reveals information about entailment relation. We study the recursive composition of this subtree-level entailment relation, which can be viewed as a soft version of the Natural Logic framework (MacCartney and Manning, 2009). Experiments show that our structured attention and entailment composition model can correctly identify and infer entailment relations from the bottom up, and bring significant improvements in accuracy.

2015

pdf bib
Search-Aware Tuning for Hierarchical Phrase-based Decoding
Feifei Zhai | Liang Huang | Kai Zhao
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Scalable Large-Margin Structured Learning: Theory and Algorithms
Liang Huang | Kai Zhao
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing: Tutorial Abstracts

pdf bib
Type-Driven Incremental Semantic Parsing with Polymorphism
Kai Zhao | Liang Huang
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Learning Translation Models from Monolingual Continuous Representations
Kai Zhao | Hany Hassan | Michael Auli
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
A hybrid system for Chinese-English patent machine translation
Hongzheng Li | Kai Zhao | Renfen Hu | Yun Zhu | Yaohong Jin
Proceedings of the 6th Workshop on Patent and Scientific Literature Translation

2014

pdf bib
Hierarchical MT Training using Max-Violation Perceptron
Kai Zhao | Liang Huang | Haitao Mi | Abe Ittycheriah
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
Scalable Large-Margin Structured Learning: Theory and Algorithms
Liang Huang | Kai Zhao | Lemao Liu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Tutorials

2013

pdf bib
Optimal Incremental Parsing via Best-First Dynamic Programming
Kai Zhao | James Cross | Liang Huang
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Online Learning for Inexact Hypergraph Search
Hao Zhang | Liang Huang | Kai Zhao | Ryan McDonald
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Max-Violation Perceptron and Forced Decoding for Scalable MT Training
Heng Yu | Liang Huang | Haitao Mi | Kai Zhao
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Minibatch and Parallelization for Online Large Margin Structured Learning
Kai Zhao | Liang Huang
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Efficient Implementation of Beam-Search Incremental Parsers
Yoav Goldberg | Kai Zhao | Liang Huang
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2010

pdf bib
Expanding Chinese Sentiment Dictionaries from Large Scale Unlabeled Corpus
Hongzhi Xu | Kai Zhao | Likun Qiu | Changjian Hu
Proceedings of the 24th Pacific Asia Conference on Language, Information and Computation

2009

pdf bib
A Hybrid Model for Sense Guessing of Chinese Unknown Words
Likun Qiu | Kai Zhao | Changjian Hu
Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Volume 2

pdf bib
SESS: A Self-Supervised and Syntax-Based Method for Sentiment Classification
Weishi Zhang | Kai Zhao | Likun Qiu | Changjian Hu
Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Volume 2

2008

pdf bib
A Method for Automatic POS Guessing of Chinese Unknown Words
Likun Qiu | Changjian Hu | Kai Zhao
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)