Many efforts have been made in solving the Aspect-based sentiment analysis (ABSA) task.
Peer review and rebuttal, with rich interactions and argumentative discussions in between, are naturally a good resource to mine arguments.
Ranked #3 on Argument Pair Extraction (APE) on RR
While there is much research on cross-domain text classification, most existing approaches focus on one-to-one or many-to-one domain adaptation.
This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair.
Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars.
We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated.
In this paper, we introduce a comprehensive probing dataset \tempreason to evaluate the temporal reasoning capability of large language models.
M3Exam exhibits three unique characteristics: (1) multilingualism, encompassing questions from multiple countries that require strong multilingual proficiency and cultural knowledge; (2) multimodality, accounting for the multimodal nature of many exam questions to test the model's multimodal understanding capability; and (3) multilevel structure, featuring exams from three critical educational periods to comprehensively assess a model's proficiency at different levels.
Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents.
For the second challenge, we leverage ImageBind, a universal embedding model aligning multiple modalities as the pre-trained audio encoder, and introduce an Audio Q-former on top of ImageBind to learn reasonable auditory query embeddings for the LLM module.
In this work, we for the first time propose a challenging argument quadruplet extraction task (AQE), which can provide an all-in-one extraction of four argumentative components, i. e., claims, evidence, evidence types, and stances.
This paper aims to provide a comprehensive investigation into the capabilities of LLMs in performing various sentiment analysis tasks, from conventional sentiment classification to aspect-based sentiment analysis and multifaceted analysis of subjective texts.
Our preliminary experiments show that generating intermediate reasoning steps does not always boost the performance of complex temporal question-answering tasks.
As large language models (LLMs) have demonstrated their powerful capabilities in plenty of domains and tasks, including context understanding, code generation, language generation, data storytelling, etc., many data analysts may raise concerns if their jobs will be replaced by AI.
Aspect Sentiment Triplet Extraction (ASTE) is a subtask of Aspect-Based Sentiment Analysis (ABSA) that considers each opinion term, their expressed sentiment, and the corresponding aspect targets.
mPMR aims to guide multilingual pre-trained language models (mPLMs) to perform natural language understanding (NLU) including both sequence classification and span extraction in multiple languages.
In cross-lingual named entity recognition (NER), self-training is commonly used to bridge the linguistic gap by training on pseudo-labeled target-language data.
Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations.
Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-commerce via presenting customers with useful reviews.
We also bring attention to the LLM's deteriorating evaluation capability with the rising qualities of summaries.
We introduce Chain of Knowledge (CoK), a framework that augments large language models with structured knowledge bases to improve factual correctness and reduce hallucination.
Recently, data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER).
First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG).
In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning.
While sentiment analysis systems try to determine the sentiment polarities of given targets based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the opinion cues come in an implicit and obscure manner.
Information extraction (IE) systems aim to automatically extract structured information, such as named entities, relations between entities, and events, from unstructured texts.
Cross-domain aspect-based sentiment analysis (ABSA) aims to perform various fine-grained sentiment analysis tasks on a target domain by transferring knowledge from a source domain.
Pre-trained language models (PLMs) have accomplished impressive achievements in abstractive single-document summarization (SDS).
As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness.
To enable further research on PEFT methods of LLMs, this paper presents LLM-Adapters, an easy-to-use framework that integrates various adapters into LLMs and can execute these adapter-based PEFT methods of LLMs for different tasks.
In addition, we introduce two new data regimes to mimic more realistic scenarios with annotation errors and evaluate our sampling strategy.
In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks.
On the basis of the findings, we recommended the application of more systematic and comprehensive psychological metrics to further evaluate and improve the safety of LLMs.
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data.
Hence, we propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers.
Ranked #1 on Hyper-Relational Extraction on HyperRED
We propose ConNER as a novel consistency training framework for cross-lingual NER, which comprises of: (1) translation-based consistency training on unlabeled target-language data, and (2) dropoutbased consistency training on labeled source-language data.
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios.
To overcome the aforementioned issues, we propose Multimodal Contrastive Learning for Multimodal Review Helpfulness Prediction (MRHP) problem, concentrating on mutual information between input modalities to explicitly elaborate cross-modal relations.
Unlike most prior work that only evaluates the ability to measure semantic similarity, we present a thorough evaluation of existing multilingual sentence embeddings and our improved versions, which include a collection of five transfer tasks in different downstream applications.
Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training.
As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data.
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.
We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset.
Traditionally, a debate usually requires a manual preparation process, including reading plenty of articles, selecting the claims, identifying the stances of the claims, seeking the evidence for the claims, etc.
Our model consistently outperforms strong baselines and its performance exceeds the previous SOTA by 1. 36 F1 and 1. 46 Ign_F1 score on the DocRED leaderboard.
Ranked #2 on Relation Extraction on DocRED
We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods.
Ranked #1 on Zero-shot Relation Triplet Extraction on Wiki-ZSL
More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks.
In this work, we explore methods to make better use of the multilingual annotation and language agnostic property of KG triples, and present novel knowledge based multilingual language models (KMLMs) trained directly on the knowledge triples.
A more useful text generator should leverage both the input text and the control signal to guide the generation, which can only be built with a deep understanding of the domain knowledge.
Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training.
Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity.
Ranked #3 on Aspect-Based Sentiment Analysis (ABSA) on TASD
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher.
Data augmentation is an effective solution to data scarcity in low-resource scenarios.
As high-quality labeled data is scarce, unsupervised sentence representation learning has attracted much attention.
Aspect-based sentiment analysis (ABSA) has received increasing attention recently.
Ranked #4 on Aspect Sentiment Triplet Extraction on ASTE-Data-V2
With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages.
In addition, we also devise an intra-review coherent reasoning module to identify the coherence between the text content and images of the review, which is a piece of strong evidence for review helpfulness prediction.
Prior research work treats this task as a sequence labeling problem and a binary classification problem on two passages that are directly concatenated together, which has a limitation of not fully utilizing the unique characteristics and inherent relations of two different passages.
Ranked #2 on Argument Pair Extraction (APE) on RR
Aspect Sentiment Triplet Extraction (ASTE) is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term.
Ranked #5 on Aspect Sentiment Triplet Extraction on ASTE-Data-V2
It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task.
We believe this is because both types of features - the contextual information captured by the linear sequences and the structured information captured by the dependency trees may complement each other.
We operationalize our framework by first proposing a novel sense-aware cross entropy loss to model word senses explicitly.
Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences.
In our architecture, we reconstruct KB triples or texts via a closed-loop framework via linking a generator and an extractor.
Experimental results show that our proposed method achieves significant performance improvements over the state-of-the-art pretrained cross-lingual language model in the CLCD setting.
Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models.
Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks.
With the help of these strategies, we are able to train a model with fewer parameters while maintaining the model capacity.
Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features.
Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach.
Ranked #3 on Aspect Sentiment Triplet Extraction on SemEval
However, SBERT is trained on corpus with high-quality labeled sentence pairs, which limits its application to tasks where labeled data is extremely scarce.
Ranked #16 on Semantic Textual Similarity on STS16
To improve the robustness of self-training, in this paper we present class-aware feature self-distillation (CFd) to learn discriminative features from PrLMs, in which PrLM features are self-distilled into a feature adaptation module and the features from the same class are more tightly clustered.
Exploiting sentence-level labels, which are easy to obtain, is one of the plausible methods to improve low-resource named entity recognition (NER), where token-level labels are costly to annotate.
We manually collect a new and high-quality paired dataset, where each pair contains an unordered product attribute set in the source language and an informative product description in the target language.
Previous works on knowledge-to-text generation take as input a few RDF triples or key-value pairs conveying the knowledge of some entities to generate a natural language description.
Ranked #1 on KG-to-Text Generation on ENT-DESC
Different from neural machine translation, in the task of text summarization, salience estimation for words, phrases or sentences is a critical component, since the output summary is a distillation of the input text.
The encoder maps the words in the input sentence into a sequence of hidden states, which are then fed into the decoder to generate the output sentence.
We propose an iterative learning framework for handling this challenge via adaptive transfer and augmentation of the training instances with the help of the available user-posed question-answer data.
In this paper, we introduce a new subtask under ABSA, named aspect sentiment triplet extraction (ASTE).
Ranked #5 on Aspect Sentiment Triplet Extraction on SemEval
Customers ask questions and customer service staffs answer their questions, which is the basic service model via multi-turn customer service (CS) dialogues on E-commerce platforms.
Emotion cause analysis, which aims to identify the reasons behind emotions, is a key topic in sentiment analysis.
Ranked #2 on Emotion Cause Extraction on ECE
Previous research on dialogue systems generally focuses on the conversation between two participants, yet multi-party conversations which involve more than two participants within one session bring up a more complicated but realistic scenario.
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Question generation (QG) is the task of generating a question from a reference sentence and a specified answer within the sentence.
In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e. g. BERT, on the E2E-ABSA task.
Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that has long suffered from the shortage of parallel data.
Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions.
Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity.
For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases.
In order to exploit the persona information, we propose a framework based on adversarial variational auto-encoders (aVAE) for persona modeling from the historical tips and reviews of users and items.
To tackle this problem, we propose the task of reader-aware abstractive summary generation, which utilizes the reader comments to help the model produce better summary about the main aspect.
Ranked #1 on Reader-Aware Summarization on RASG
Target-based sentiment analysis involves opinion target extraction and target sentiment classification.
Inferring the agreement/disagreement relation in debates, especially in online debates, is one of the fundamental tasks in argumentation mining.
Recurrent neural network language models (RNNLMs) are the current standard-bearer for statistical language modeling.
Combining the virtues of probability graphic models and neural networks, Conditional Variational Auto-encoder (CVAE) has shown promising performance in applications such as response generation.
We investigate the task of distractor generation for multiple choice reading comprehension questions from examinations.
We investigate the difficulty levels of questions in reading comprehension datasets such as SQuAD, and propose a new question generation setting, named Difficulty-controllable Question Generation (DQG).
Given reviews from different domains, some existing methods for word embeddings exploit sentiment information, but they cannot produce domain-sensitive embeddings.
Between the two layers, we propose a component to generate target-specific representations of words in the sentence, meanwhile incorporate a mechanism for preserving the original contextual information from the RNN layer.
Ranked #19 on Aspect-Based Sentiment Analysis (ABSA) on SemEval 2014 Task 4 Sub Task 2 (Laptop (Acc) metric)
Aspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews.
We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL).
For example, an input sequence could be a word sequence, such as review sentence and advertisement text.
For the critic, we combine the maximum likelihood estimator with a well designed global summary quality estimator which is a neural network based binary classifier aiming to make the generated summaries indistinguishable from the human-written ones.
We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review.
The attention weights are learned automatically by an unsupervised data reconstruction framework which can capture the sentence salience.
We investigate the problem of reader-aware multi-document summarization (RA-MDS) and introduce a new dataset for this problem.
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN).
Ranked #5 on Text Summarization on DUC 2004 Task 1
In essence, writing some tips and giving a numerical rating are two facets of a user's product assessment action, expressing the user experience and feelings.
We propose a general approach to modeling semi-supervised learning (SSL) algorithms.
We propose a framework to improve performance of distantly-supervised relation extraction, by jointly learning to solve two related tasks: concept-instance extraction and relation extraction.
We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases.
We propose a new MDS paradigm called reader-aware multi-document summarization (RA-MDS).