no code implementations • Findings (EMNLP) 2021 • Yaochen Liu, Yazhou Zhang, Qiuchi Li, Benyou Wang, Dawei Song
The QPM framework involves a complex-valued multi-modal representation encoder, a quantum-like fusion subnetwork and a quantum measurement mechanism.
no code implementations • NAACL 2022 • Ao Jia, Yu He, Yazhou Zhang, Sagar Uprety, Dawei Song, Christina Lioma
Desire is a strong wish to do or have something, which involves not only a linguistic expression, but also underlying cognitive phenomena driving human feelings.
no code implementations • 4 Mar 2024 • Si Sun, Hanqing Zhang, Zhiyuan Liu, Jie Bao, Dawei Song
Dense Retrieval (DR) is now considered as a promising tool to enhance the memorization capacity of Large Language Models (LLM) such as GPT3 and GPT-4 by incorporating external memories.
1 code implementation • 13 Nov 2023 • Chen Zhang, Dawei Song, Zheyu Ye, Yan Gao
The pain is mainly resulted by the curse of capacity gap, which describes that a larger teacher LM cannot always lead to a better student LM than one distilled from a smaller teacher LM due to the affect of capacity gap increment.
no code implementations • 13 Nov 2023 • Chen Zhang, Benyou Wang, Dawei Song
To this end, we propose an elastic language model (ElasticLM) that elastically adjusts the tradeoff according to the request stream.
no code implementations • 7 Nov 2023 • Ruize An, Chen Zhang, Dawei Song
Recently, SimCSE has shown the feasibility of contrastive learning in training sentence embeddings and illustrates its expressiveness in spanning an aligned and uniform embedding space.
2 code implementations • 28 Sep 2023 • Hanqing Zhang, Sun Si, Haiming Wu, Dawei Song
Large-scale Causal Language Models (CLMs), e. g., GPT3 and ChatGPT, have brought great success in text generation.
no code implementations • 6 Jun 2023 • Yaochen Liu, Qiuchi Li, Benyou Wang, Yazhou Zhang, Dawei Song
Quantum theory, originally proposed as a physical theory to describe the motions of microscopic particles, has been applied to various non-physics domains involving human cognition and decision-making that are inherently uncertain and exhibit certain non-classical, quantum-like characteristics.
no code implementations • 6 Jun 2023 • Yaochen Liu, Yazhou Zhang, Dawei Song
In view of the recent success of quantum probability (QP) in modeling human cognition, particularly contextual incompatible decision making, we take the first step towards introducing QP into joint multi-modal sarcasm, sentiment, and emotion analysis.
no code implementations • 21 May 2023 • Chen Zhang, Yang Yang, Jingang Wang, Dawei Song
Finetuning pretrained language models (LMs) have enabled appealing performance on a diverse array of tasks.
1 code implementation • 20 May 2023 • Chen Zhang, Yang Yang, Jiahao Liu, Jingang Wang, Yunsen Xian, Benyou Wang, Dawei Song
However, when the capacity gap between the teacher and the student is large, a curse of capacity gap appears, invoking a deficiency in distilling LMs.
1 code implementation • 23 Mar 2023 • Juhao Liang, Chen Zhang, Zhengyang Tang, Jie Fu, Dawei Song, Benyou Wang
Built upon the paradigm, we propose a retrieval model with modular prompt tuning named REMOP.
1 code implementation • 18 Oct 2022 • Hanqing Zhang, Dawei Song
Prompt learning with immensely large Casual Language Models (CLMs) has been shown promising for attribute-controllable text generation (CTG).
no code implementations • 10 Oct 2022 • Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan, Dawei Song
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner.
1 code implementation • 8 Oct 2022 • Yi Yang, Chen Zhang, Dawei Song
Recent advances in distilling pretrained language models have discovered that, besides the expressiveness of knowledge, the student-friendliness should be taken into consideration to realize a truly knowledgable teacher.
1 code implementation • COLING 2022 • Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, Dawei Song
Thus, a natural question arises: Is structural bias still a necessity in the context of PLMs?
1 code implementation • 20 Jul 2022 • Yi Yang, Chen Zhang, Benyou Wang, Dawei Song
To uncover the domain-general LM, we propose to identify domain-general parameters by playing lottery tickets (dubbed doge tickets).
1 code implementation • 17 Jul 2022 • Fang Ma, Chen Zhang, Bo Zhang, Dawei Song
Extensive experimental results on standard and adversarial benchmarks for SC and OE demonstrate the effectiveness and robustness of the proposed method, yielding new state-of-the-art performance on OE and competitive performance on SC.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 17 Jul 2022 • Jinglin Wang, Fang Ma, Yazhou Zhang, Dawei Song
Multimodal emotion recognition in conversations (mERC) is an active research topic in natural language processing (NLP), which aims to predict human's emotional states in communications of multiple modalities, e, g., natural language and facial gestures.
1 code implementation • 29 May 2022 • Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, Dawei Song
In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $\lambda$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student.
1 code implementation • 11 May 2022 • Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, Dawei Song
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge.
no code implementations • 27 Apr 2022 • Bo Zhang, Chen Zhang, Fang Ma, Dawei Song
Neural text matching models have been used in a range of applications such as question answering and natural language inference, and have yielded a good performance.
no code implementations • 16 Mar 2022 • Xiang Li, Yazhou Zhang, Prayag Tiwari, Dawei Song, Bin Hu, Meihong Yang, Zhigang Zhao, Neeraj Kumar, Pekka Marttinen
Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic.
no code implementations • 14 Jan 2022 • Hanqing Zhang, Haolin Song, Shaoyu Li, Ming Zhou, Dawei Song
In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text.
1 code implementation • Findings (ACL) 2021 • Fang Ma, Chen Zhang, Dawei Song
Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence.
no code implementations • 12 Jan 2021 • Dimitris Gkoumas, Qiuchi Li, Shahram Dehdashti, Massimo Melucci, Yijun Yu, Dawei Song
Thus the cognitive process exhibits "quantum-like" biases that cannot be captured by classical probability theories.
3 code implementations • Findings of the Association for Computational Linguistics 2020 • Chen Zhang, Qiuchi Li, Dawei Song, Benyou Wang
The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms.
Aspect-Based Sentiment Analysis Aspect Sentiment Triplet Extraction +2
no code implementations • 19 Sep 2020 • Chenguang Zhang, Yuexian Hou, Dawei Song, Liangzhu Ge, Yaoshuai Yao
In this paper, from an information theoretic perspective, we introduce a new definition of redundancy to describe the diversity of hidden units under supervised learning settings by formalizing the effect of hidden layers on the generalization capacity as the mutual information.
no code implementations • 8 Jul 2020 • Sagar Uprety, Dimitris Gkoumas, Dawei Song
Since 2004, researchers have been using the mathematical framework of Quantum Theory (QT) in Information Retrieval (IR).
2 code implementations • 25 Feb 2020 • Haolin Song, Chen Zhang, Qiuchi Li, Dawei Song
Specifically, our model regards pair extraction as a link prediction task, and learns to link from emotion clauses to cause clauses, i. e., the links are directional.
Ranked #12 on Emotion-Cause Pair Extraction on ECPE
no code implementations • 18 Feb 2020 • Cheng Zhang, Qiuchi Li, Lingyu Hua, Dawei Song
To tackle the problem, in this paper, we identify and analyze the internal and external factors that affect the memory ability of RNNs, and propose a Semantic Euclidean Space to represent the semantics expressed by a sequence.
no code implementations • 20 Jan 2020 • Sagar Uprety, Prayag Tiwari, Shahram Dehdashti, Lauren Fell, Dawei Song, Peter Bruza, Massimo Melucci
A large number of studies in cognitive science have revealed that probabilistic outcomes of certain human decisions do not agree with the axioms of classical probability theory.
no code implementations • 25 Sep 2019 • Peng Zhang, Xiaoliu Mao, Xindian Ma, Benyou Wang, Jing Zhang, Jun Wang, Dawei Song
We prove that by a mapping (via the trace operator) on the high-dimensional matching matrix, a low-dimensional attention matrix can be derived.
1 code implementation • 23 Sep 2019 • Chen Zhang, Qiuchi Li, Dawei Song
It has been widely accepted that Long Short-Term Memory (LSTM) network, coupled with attention mechanism and memory module, is useful for aspect-level sentiment classification.
2 code implementations • IJCNLP 2019 • Chen Zhang, Qiuchi Li, Dawei Song
Due to their inherent capability in semantic alignment of aspects and their context words, attention mechanism and Convolutional Neural Networks (CNNs) are widely applied for aspect-based sentiment classification.
no code implementations • 25 Jul 2019 • Sagar Uprety, Shahram Dehdashti, Lauren Fell, Peter Bruza, Dawei Song
We study the interaction between the relevance dimensions using the mathematical framework of Quantum Theory.
no code implementations • 12 Jul 2019 • Yazhou Zhang, Lingling Song, Dawei Song, Peng Guo, Junwei Zhang, Peng Zhang
Existing sentiment analysis approaches are insufficient in modelling the interactions among people.
1 code implementation • NeurIPS 2019 • Xindian Ma, Peng Zhang, Shuai Zhang, Nan Duan, Yuexian Hou, Dawei Song, Ming Zhou
In this paper, based on the ideas of tensor decomposition and parameters sharing, we propose a novel self-attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition (BTD).
1 code implementation • 26 Feb 2019 • Benyou Wang, Qiuchi Li, Massimo Melucci, Dawei Song
To address this issue, we propose a new framework that models different levels of semantic units (e. g. sememe, word, sentence, and semantic abstraction) on a single \textit{Semantic Hilbert Space}, which naturally admits a non-linear semantic composition by means of a complex-valued vector word representation.
1 code implementation • 31 Jan 2019 • Lipeng Zhang, Peng Zhang, Xindian Ma, Shuqin Gu, Zhan Su, Dawei Song
Theoretically, we prove that such tensor representation is a generalization of the n-gram language model.
no code implementations • 16 Nov 2018 • Sagar Uprety, Dimitris Gkoumas, Dawei Song
Relevance judgment in Information Retrieval is influenced by multiple factors.
1 code implementation • 28 Aug 2018 • Peng Zhang, Zhan Su, Lipeng Zhang, Benyou Wang, Dawei Song
The recently proposed quantum language model (QLM) aimed at a principled approach to modeling term dependency by applying the quantum probability theory.
no code implementations • 14 Aug 2018 • Sagar Uprety, Dawei Song
There are many examples of human decision making which cannot be modeled by classical probabilistic and logic models, on which the current AI systems are based.
no code implementations • 14 Jul 2018 • Sagar Uprety, Dawei Song
There is a growing body of research which has investigated relevance judgment in IR being influenced by multiple factors or dimensions.
no code implementations • WS 2018 • Qiuchi Li, Sagar Uprety, Benyou Wang, Dawei Song
A challenging task for word embeddings is to capture the emergent meaning or polarity of a combination of individual words.
1 code implementation • 12 Dec 2016 • Thanh Vu, Dat Quoc Nguyen, Mark Johnson, Dawei Song, Alistair Willis
Recent research has shown that the performance of search personalization depends on the richness of user profiles which normally represent the user's topical interests.
no code implementations • 5 Feb 2015 • Xiaozhao Zhao, Yuexian Hou, Dawei Song, Wenjie Li
We then revisit Boltzmann machines (BM) from a model selection perspective and theoretically show that both the fully visible BM (VBM) and the BM with hidden units can be derived from the general binary multivariate distribution using the CIF principle.
no code implementations • 16 Feb 2013 • Xiaozhao Zhao, Yuexian Hou, Qian Yu, Dawei Song, Wenjie Li
Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data.