Wai Lam

Reader Comment Digest through Latent Event Facets and News Specificity

2018 · IEEE Transactions on Knowledge and Data Engineering

When a significant event occurs, many news articles from different newsagents often report it. Moreover, these newsagents also provide platforms for their readers to write comments expressing their views or understanding. Through digesting these reader …

Product Question Intent Detection using Indicative Clause Attention and Adversarial Learning

2018

Due to the provision of QA service in many E-commerce sites, product question understanding becomes important. Product questions have different characteristics from traditional questions in that they are long and verbose as well as associated …

Learning Domain-Sensitive and Sentiment-Aware Word Embeddings

2018

Word embeddings have been widely used in sentiment classification because of their efficacy for semantic representations of words. Given reviews from different domains, some existing methods for word embeddings exploit sentiment information, but they cannot …

Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion

2019 · arXiv (Cornell University)

For large-scale knowledge graphs (KGs), recent research has been focusing on the large proportion of infrequent relations which have been ignored by previous studies. For example few-shot learning paradigm for relations has been investigated. In …

Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization

2020

Non-factoid question answering (QA) is one of the most extensive yet challenging application and research areas of retrieval-based question answering. In particular, answers to non-factoid questions can often be too lengthy and redundant to comprehend, …

Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We introduce a data-driven approach to generating derivation trees from meaning representation graphs with probabilistic synchronous hyperedge replacement grammar (PSHRG). SHRG has been used to produce meaning representation graphs from texts and syntax trees, but …

Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation

2022 · arXiv (Cornell University)

Despite the fact that multilingual agreement (MA) has shown its importance for multilingual neural machine translation (MNMT), current methodologies in the field have two shortages: (i) require parallel data between multiple language pairs, which is …

CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite

2024 · arXiv (Cornell University)

Generative query rewrite generates reconstructed query rewrites using the conversation history while rely heavily on gold rewrite pairs that are expensive to obtain. Recently, few-shot learning is gaining increasing popularity for this task, whereas these …

Salience Estimation via Variational Auto-Encoders for Multi-Document Summarization

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

We propose a new unsupervised sentence salience framework for Multi-Document Summarization (MDS), which can be divided into two components: latent semantic modeling and salience estimation. For latent semantic modeling, a neural generative model called Variational …

Jointly Learning Word Embeddings and Latent Topics

2017

Word embedding models such as Skip-gram learn a vector-space representation for each word, based on the local word collocation patterns that are observed in a text corpus. Latent topic models, on the other hand, take …

Neural Rating Regression with Abstractive Tips Generation for Recommendation

2017

Recently, some E-commerce sites launch a new interaction box called Tips on their mobile apps. Users can express their experience and feelings or provide suggestions using short texts typically several words or one sentence. In …

Graph Transformer for Graph-to-Sequence Learning

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons. Unlike graph neural networks that restrict the information exchange between …

Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning

2021

Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what …