Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words. However, the underlying reasons for their strong performance have not been well explained. In this paper, we bridge the gap by assessing the strengths of selective SANs (SSANs), which are implemented with a flexible and universal Gumbel-Softmax. Experimental results on several representative NLP tasks, including natural language inference, semantic role labelling, and machine translation, show that SSANs consistently outperform the standard SANs. Through well-designed probing experiments, we empirically validate that the improvement of SSANs can be attributed in part to mitigating two commonly-cited weaknesses of SANs: word order encoding and structure modeling. Specifically, the selective mechanism improves SANs by paying more attention to content words that contribute to the meaning of the sentence. The code and data are released at https://github.com/xwgeng/SSAN.
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）；Northeastern University（东北大学）
Aspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews. We present a new framework for tackling ATE. It can exploit two useful clues, namely opinion summary and aspect detection history. Opinion summary is distilled from the whole input sentence, conditioned on each current token for aspect prediction, and thus the tailor-made summary can help aspect prediction on this token. Another clue is the information of aspect detection history, and it is distilled from the previous aspect predictions so as to…
In order to equip NLP systems with selective prediction capability, several task-specific approaches have been proposed. However, which approaches work best across tasks or even if they consistently outperform the simplest baseline 'MaxProb' remains to be explored. To this end, we systematically study 'selective prediction' in a large-scale setup of 17 datasets across several NLP tasks. Through comprehensive experiments under in-domain (IID), out-of-domain (OOD), and adversarial (ADV) settings, we show that despite leveraging additional resources (held-out data/computation), none of the existi…
IBM Corporation（IBM公司）；North Carolina State University（北卡罗来纳州立大学）
Sentiments in opinionated text are often determined by both aspects and target words (or targets). We observe that targets and aspects interrelate in subtle ways, often yielding conflicting sentiments. Thus, a naive aggregation of sentiments from aspects and targets treated separately, as in existing sentiment analysis models, impairs performance. We propose Octa, an approach that jointly considers aspects and targets when inferring sentiments. To capture and quantify relationships between targets and context words, Octa uses a selective self-attention mechanism that handles implicit or missin…
Aspect-level sentiment classification aims to identify the sentiment polarity towards a specific aspect term in a sentence. Most current approaches mainly consider the semantic information by utilizing attention mechanisms to capture the interactions between the context and the aspect term. In this paper, we propose to employ graph convolutional networks (GCNs) on the dependency tree to learn syntax-aware representations of aspect terms. GCNs often show the best performance with two layers, and deeper GCNs do not bring additional gain due to over-smoothing problem. However, in some cases, impo…
DiDi Chuxing（滴滴出行）；DiDi Research America（美国滴滴研究院）；Peking University（北京大学）
Abstractive text summarization is a challenging task, and one need to design a mechanism to effectively extract salient information from the source text and then generate a summary. A parsing process of the source text contains critical syntactic or semantic structures, which is useful to generate more accurate summary. However, modeling a parsing tree for text summarization is not trivial due to its non-linear structure and it is harder to deal with a document that includes multiple sentences and their parsing trees. In this paper, we propose to use a graph to connect the parsing trees from t…
SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Chongqing University（重庆大学）；Peng Cheng Laboratory（鹏城实验室）；Wuhan AI Research（武汉人工智能研究院）
Monash University（莫纳什大学）；Unbabel；Instituto de Telecomunicações（电信研究所）
Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or w…
University of Technology Sydney（悉尼科技大学）；University of Washington（华盛顿大学）；University of New South Wales（新南威尔士大学）
Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly labeled data, which however could be incompetent when there is only one sentence in a bag. In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. Specifically, in the proposed framework, 1) we use an entity-aware word…
Zhejiang University（浙江大学）；University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Hikvision Research Institute（海康威视研究院）；University of Southern California（南加利福尼亚大学）
Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations. However, the generated training data typically contain massive noise, and may result in poor performances with the vanilla supervised learning. In this paper, we propose to conduct multi-instance learning with a novel Cross-relation Cross-bag Selective Attention (C$^2$SA), which leads to noise-robust training for distant supervised relation extractor. Specifically, we employ the sentence-level selective attention to reduce the effect of noisy o…
Singapore University of Technology and Design（新加坡科技设计大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
With the boom of e-commerce, Multimodal Review Helpfulness Prediction (MRHP), which aims to sort product reviews according to the predicted helpfulness scores has become a research hotspot. Previous work on this task focuses on attention-based modality fusion, information integration, and relation modeling, which primarily exposes the following drawbacks: 1) the model may fail to capture the really essential information due to its indiscriminate attention formulation; 2) lack appropriate modeling methods that take full advantage of correlation among provided data. In this paper, we propose SAN…
Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）
Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation. However, little attention is paid to inaugurate more diverse context for abundant context information. In this paper, we propose a Selective Memory-augmented Neural Document Translation model to deal with documents containing large hypothesis space of the context. Specifically, we retrieve similar bilingual sentence pairs from the training corpus to augment global context and then extend the two-stream attention model with selective me…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Research（微软研究院）
We propose a selective encoding model to extend the sequence-to-sequence framework for abstractive sentence summarization. It consists of a sentence encoder, a selective gate network, and an attention equipped decoder. The sentence encoder and decoder are built with recurrent neural networks. The selective gate network constructs a second level sentence representation by controlling the information flow from encoder to decoder. The second level representation is tailored for sentence summarization task, which leads to better performance. We evaluate our model on the English Gigaword, DUC 2004 …
Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；National University of Singapore（新加坡国立大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）
Video captioning works on the two fundamental concepts, feature detection and feature composition. While modern day transformers are beneficial in composing features, they lack the fundamental problems of selecting and understanding of the contents. As the feature length increases, it becomes increasingly important to include provisions for improved capturing of the pertinent contents. In this work, we have introduced a new concept of Self-Aware Composition Transformer (SACT) that is capable of generating Multinomial Attention (MultAtt) which is a way of generating distributions of various com…
