Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to overcome the challenge. In this paper, we study the length generalization property of NoPE. We find that although NoPE can extend to longer sequences than the commonly used explicit position encodings, it still has a limited context length. We identify a connection between the failure of NoPE’s generalization and the distraction of attention distributions. We propose a parameter-efficient tuning for searching attention heads’ best temperature hyper-parameters, which substantially expands NoPE’s context size. Experiments on long sequence language modeling, the synthetic passkey retrieval task and real-world long context tasks show that NoPE can achieve competitive performances with state-of-the-art length generalization algorithms. The source code is publicly accessible

Implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis due to the absence of connectives. Most existing methods utilize one-hot labels as the sole optimization target, ignoring the internal association among connectives. Besides, these approaches spend lots of effort on template construction, negatively affecting the generalization capability. To address these problems,we propose a novel Connective Prediction via Knowledge Distillation (CP-KD) approach to instruct large-scale pre-trained language models (PLMs) mining the latent correlations between connectives and discourse relations, which is meaningful for IDRR. Experimental results on the PDTB 2.0/3.0 and CoNLL2016 datasets show that our method significantly outperforms the state-of-the-art models on coarse-grained and fine-grained discourse relations. Moreover, our approach can be transferred to explicit discourse relation recognition(EDRR) and achieve acceptable performance.

We study the problem of defying catastrophic forgetting when learning a series of language processing tasks. Compared with previous methods, we emphasize the importance of not caching history tasks’ data, which makes the problem more challenging. Our proposed method applies the parameter isolation strategy. For each task, it allocates a small portion of private parameters and learns them with a shared pre-trained model. To load correct parameters at testing time, we introduce a simple yet effective non-parametric method. Experiments on continual language learning benchmarks show that our method is significantly better than all existing no-data-cache methods, and is comparable (or even better) than those using historical data.

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning ability on many NLP tasks. A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it. However, it is nontrivial to perform information extraction (IE) tasks with NL-LLMs since the output of the IE task is usually structured and therefore is hard to be converted into plain text. In this paper, we propose to recast the structured output in the form of code instead of natural language and utilize generative LLMs of code (Code-LLMs) such as Codex to perform IE tasks, in particular, named entity recognition and relation extraction. In contrast to NL-LLMs, we show that Code-LLMs can be well-aligned with these IE tasks by designing code-style prompts and formulating these IE tasks as code generation tasks. Experiment results on seven benchmarks show that our method consistently outperforms fine-tuning moderate-size pre-trained models specially designed for IE tasks (e.g., UIE) and prompting NL-LLMs under few-shot settings. We further conduct a series of in-depth analyses to demonstrate the merits of leveraging Code-LLMs for IE tasks.

Existing models for named entity recognition (NER) are mainly based on large-scale labeled datasets, which always obtain using crowdsourcing. However, it is hard to obtain a unified and correct label via majority voting from multiple annotators for NER due to the large labeling space and complexity of this task. To address this problem, we aim to utilize the original multi-annotator labels directly. Particularly, we propose a CONfidence-based partial Label Learning (CONLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER. This model learns a token- and content-dependent confidence via an Expectation–Maximization (EM) algorithm by minimizing empirical risk. The true posterior estimator and confidence estimator perform iteratively to update the true posterior and confidence respectively. We conduct extensive experimental results on both real-world and synthetic datasets, which show that our model can improve performance effectively compared with strong baselines.

Recent multilingual models benefit from strong unified semantic representation models. However, due to conflict linguistic regularities, ignoring language-specific features during multilingual learning may suffer from negative transfer. In this work, we analyze the relationbetween a language’s position space and its typological characterization, and suggest deploying different position spaces for different languages. We develop a position generation network which combines prior knowledge from typology features and existing position vectors. Experiments on the multilingual dependency parsing task show that the learned position vectors exhibit meaningful hidden structures, and they can help achieving the best multilingual parsing results.

This paper introduces the Chinese Essay Discourse Coherence Corpus (CEDCC), a multi-task dataset for assessing discourse coherence. Existing research tends to focus on isolated dimensions of discourse coherence, a gap which the CEDCC addresses by integrating coherence grading, topical continuity, and discourse relations. This approach, alongside detailed annotations, captures the subtleties of real-world texts and stimulates progress in Chinese discourse coherence analysis. Our contributions include the development of the CEDCC, the establishment of baselines for further research, and the demonstration of the impact of coherence on discourse relation recognition and automated essay scoring. The dataset and related codes is available at https://github.com/cubenlp/CEDCC_corpus.

“This paper provides a comprehensive review of the CCL23-Eval Task 8, i.e., Chinese EssayFluency Evaluation (CEFE). The primary aim of this task is to systematically identify the typesof grammatical fine-grained errors that affect the readability and coherence of essays writtenby Chinese primary and secondary school students, and then to suggest suitable corrections toenhance the fluidity of their written expression. This task consists of three distinct tracks: (1)Coarse-grained and fine-grained error identification; (2) Character-level error identification andcorrection; (3) Error sentence rewriting. In the end, we received 44 completed registration forms,leading to a total of 130 submissions from 11 dedicated participating teams. We present theresults of all participants and our analysis of these results. Both the dataset and evaluation toolused in this task are available1.”

Knowledge base (KB) embeddings have been shown to contain gender biases. In this paper, we study two questions regarding these biases: how to quantify them, and how to trace their origins in KB? Specifically, first, we develop two novel bias measures respectively for a group of person entities and an individual person entity. Evidence of their validity is observed by comparison with real-world census data. Second, we use the influence function to inspect the contribution of each triple in KB to the overall group bias. To exemplify the potential applications of our study, we also present two strategies (by adding and removing KB triples) to mitigate gender biases in KB embeddings.

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step to bridging and integrating multi-source KGs. In this paper, we argue that existing complex EA methods inevitably inherit the inborn defects from their neural network lineage: poor interpretability and weak scalability. Inspired by recent studies, we reinvent the classical Label Propagation algorithm to effectively run on KGs and propose a neural-free EA framework — LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Operation.According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many. Besides, due to the computational process of LightEA being entirely linear, we could trace the propagation process at each step and clearly explain how the entities are aligned.

Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis. Most of the current work adopted multitask learning to aid IDRR through explicit discourse relation recognition (EDRR) or utilized dependencies between discourse relation labels to constrain model predictions. But these methods still performed poorly on fine-grained IDRR and even utterly misidentified on most of the few-shot discourse relation classes. To address these problems, we propose a novel Prompt-based Connective Prediction (PCP) method for IDRR. Our method instructs large-scale pre-trained models to use knowledge relevant to discourse relation and utilizes the strong correlation between connectives and discourse relation to help the model recognize implicit discourse relations. Experimental results show that our method surpasses the current state-of-the-art model and achieves significant improvements on those fine-grained few-shot discourse relation. Moreover, our approach is able to be transferred to EDRR and obtain acceptable results. Our code is released in https://github.com/zh-i9/PCP-for-IDRR.

Syntactic trees have been widely applied in relation extraction (RE). However, since parsing qualities are not stable on different text domains and a pre-defined grammar may not well fit the target relation schema, the introduction of syntactic structures sometimes fails to improve RE performances consistently. In this work, we study RE models with various unsupervised structures mined from pre-trained language models (e.g., BERT). We show that, similar to syntactic trees, unsupervised structures are quite informative for RE task: they are able to obtain competitive (even the best) performance scores on benchmark RE datasets (ACE05, WebNLG, SciERC). We also conduct detailed analyses on their abilities of adapting new RE domains and influence of noise links in those structures. The results suggest that unsupervised structures are reasonable alternatives of commonly used syntactic structures in relation extraction models.

Existing distantly supervised relation extractors usually rely on noisy data for both model training and evaluation, which may lead to garbage-in-garbage-out systems. To alleviate the problem, we study whether a small clean dataset could help improve the quality of distantly supervised models. We show that besides getting a more convincing evaluation of models, a small clean dataset also helps us to build more robust denoising models. Specifically, we propose a new criterion for clean instance selection based on influence functions. It collects sample-level evidence for recognizing good instances (which is more informative than loss-level evidence). We also propose a teacher-student mechanism for controlling purity of intermediate results when bootstrapping the clean set. The whole approach is model-agnostic and demonstrates strong performances on both denoising real (NYT) and synthetic noisy datasets.

Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks’ label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell’s label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.

Modelling a word’s polarity in different contexts is a key task in sentiment analysis. Previous works mainly focus on domain dependencies, and assume words’ sentiments are invariant within a specific domain. In this paper, we relax this assumption by binding a word’s sentiment to its collocation words instead of domain labels. This finer view of sentiment contexts is particularly useful for identifying commonsense sentiments expressed in neural words such as “big” and “long”. Given a target (e.g., an aspect), we propose an effective “perturb-and-see” method to extract sentiment words modifying it from large-scale datasets. The reliability of the obtained target-aware sentiment lexicons is extensively evaluated both manually and automatically. We also show that a simple application of the lexicon is able to achieve highly competitive performances on the unsupervised opinion relation extraction task.

Current state-of-the-art systems for joint entity relation extraction (Luan et al., 2019; Wad-den et al., 2019) usually adopt the multi-task learning framework. However, annotations for these additional tasks such as coreference resolution and event extraction are always equally hard (or even harder) to obtain. In this work, we propose a pre-training method ENPAR to improve the joint extraction performance. ENPAR requires only the additional entity annotations that are much easier to collect. Unlike most existing works that only consider incorporating entity information into the sentence encoder, we further utilize the entity pair information. Specifically, we devise four novel objectives,i.e., masked entity typing, masked entity prediction, adversarial context discrimination, and permutation prediction, to pre-train an entity encoder and an entity pair encoder. Comprehensive experiments show that the proposed pre-training method achieves significant improvement over BERT on ACE05, SciERC, and NYT, and outperforms current state-of-the-art on ACE05.

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs (Knowledge Graphs), which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. However, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNN-based methods, we successfully transform the cross-lingual EA problem into an assignment problem. Based on this re-definition, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments have been conducted to show that our proposed unsupervised approach even beats advanced supervised methods across all public datasets while having high efficiency, interpretability, and stability.

Adapting word order from one language to another is a key problem in cross-lingual structured prediction. Current sentence encoders (e.g., RNN, Transformer with position embeddings) are usually word order sensitive. Even with uniform word form representations (MUSE, mBERT), word order discrepancies may hurt the adaptation of models. In this paper, we build structured prediction models with bag-of-words inputs, and introduce a new reordering module to organizing words following the source language order, which learns task-specific reordering strategies from a general-purpose order predictor model. Experiments on zero-shot cross-lingual dependency parsing, POS tagging, and morphological tagging show that our model can significantly improve target language performances, especially for languages that are distant from the source language.

Transition systems usually contain various dynamic structures (e.g., stacks, buffers). An ideal transition-based model should encode these structures completely and efficiently. Previous works relying on templates or neural network structures either only encode partial structure information or suffer from computation efficiency. In this paper, we propose a novel attention-based encoder unifying representation of all structures in a transition system. Specifically, we separate two views of items on structures, namely structure-invariant view and structure-dependent view. With the help of parallel-friendly attention network, we are able to encoding transition states with O(1) additional complexity (with respect to basic feature extractors). Experiments on the PTB and UD show that our proposed method significantly improves the test speed and achieves the best transition-based model, and is comparable to state-of-the-art methods.

Pre-trained language models have been widely applied to cross-domain NLP tasks like sentiment analysis, achieving state-of-the-art performance. However, due to the variety of users’ emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain. In this paper, we pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets, and utilize it for cross-domain sentiment analysis task without fine-tuning. We propose several pre-training tasks based on existing lexicons and annotations at both token and sentence levels, such as emoticons, sentiment words, and ratings, without human interference. A series of experiments are conducted and the results indicate the great advantages of our model. We obtain new state-of-the-art results in all the cross-domain sentiment analysis tasks, and our proposed SentiX can be trained with only 1% samples (18 samples) and it achieves better performance than BERT with 90% samples.

We propose a novel linearization of a constituent tree, together with a new locally normalized model. For each split point in a sentence, our model computes the normalizer on all spans ending with that split point, and then predicts a tree span from them. Compared with global models, our model is fast and parallelizable. Different from previous local models, our linearization method is tied on the spans directly and considers more local features when performing span prediction, which is more interpretable and effective. Experiments on PTB (95.8 F1) and CTB (92.4 F1) show that our model significantly outperforms existing local models and efficiently achieves competitive results with global models.

In this paper, we integrate span-related information into pre-trained encoder for entity relation extraction task. Instead of using general-purpose sentence encoder (e.g., existing universal pre-trained models), we introduce a span encoder and a span pair encoder to the pre-training network, which makes it easier to import intra-span and inter-span information into the pre-trained model. To learn the encoders, we devise three customized pre-training objectives from different perspectives, which target on tokens, spans, and span pairs. In particular, a span encoder is trained to recover a random shuffling of tokens in a span, and a span pair encoder is trained to predict positive pairs that are from the same sentences and negative pairs that are from different sentences using contrastive loss. Experimental results show that the proposed pre-training method outperforms distantly supervised pre-training, and achieves promising performance on two entity relation extraction benchmark datasets (ACE05, SciERC).

We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.

We investigate the problem of efficiently incorporating high-order features into neural graph-based dependency parsing. Instead of explicitly extracting high-order features from intermediate parse trees, we develop a more powerful dependency tree node representation which captures high-order information concisely and efficiently. We use graph neural networks (GNNs) to learn the representations and discuss several new configurations of GNN’s updating and aggregation functions. Experiments on PTB show that our parser achieves the best UAS and LAS on PTB (96.0%, 94.3%) among systems without using any external resources.

Word embeddings have been widely used to study gender stereotypes in texts. One key problem regarding existing bias scores is to evaluate their validities: do they really reflect true bias levels? For a small set of words (e.g. occupations), we can rely on human annotations or external data. However, for most words, evaluating the correctness of them is still an open problem. In this work, we utilize word association test, which contains rich types of word connections annotated by human participants, to explore how gender stereotypes spread within our minds. Specifically, we use random walk on word association graph to derive bias scores for a large amount of words. Experiments show that these bias scores correlate well with bias in the real world. More importantly, comparing with word-embedding-based bias scores, it provides a different perspective on gender stereotypes in words.

We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).

We investigate the task of joint entity relation extraction. Unlike prior efforts, we propose a new lightweight joint learning paradigm based on minimum risk training (MRT). Specifically, our algorithm optimizes a global loss function which is flexible and effective to explore interactions between the entity model and the relation model. We implement a strong and simple neural network where the MRT is executed. Experiment results on the benchmark ACE05 and NYT datasets show that our model is able to achieve state-of-the-art joint extraction performances.

This paper describes our submissions to SemEval 2018 task 1. The task is affect intensity prediction in tweets, including five subtasks. We participated in all subtasks of English tweets. We extracted several traditional NLP, sentiment lexicon, emotion lexicon and domain specific features from tweets, adopted supervised machine learning algorithms to perform emotion intensity prediction.

This paper describes our submissions to Task 2 in SemEval 2018, i.e., Multilingual Emoji Prediction. We first investigate several traditional Natural Language Processing (NLP) features, and then design several deep learning models. For subtask 1: Emoji Prediction in English, we combine two different methods to represent tweet, i.e., supervised model using traditional features and deep learning model. For subtask 2: Emoji Prediction in Spanish, we only use deep learning model.

This paper describes the system we submitted to Task 10 (Capturing Discriminative Attributes) in SemEval 2018. Given a triple (word1, word2, attribute), this task is to predict whether it exemplifies a semantic difference or not. We design and investigate several word embedding features, PMI features and WordNet features together with supervised machine learning methods to address this task. Officially released results show that our system ranks above average.

This paper describes the system we submitted to the Task 11 in SemEval 2018, i.e., Machine Comprehension using Commonsense Knowledge. Given a passage and some questions that each have two candidate answers, this task requires the participate system to select out one answer meet the meaning of original text or commonsense knowledge from the candidate answers. For this task, we use a deep learning method to obtain final predict answer by calculating relevance of choices representations and question-aware document representation.

This paper presents our submissions to SemEval 2018 Task 12: the Argument Reasoning Comprehension Task. We investigate an end-to-end attention-based neural network to represent the two lexically close candidate warrants. On the one hand, we extract their different parts as attention vectors to obtain distinguishable representations. On the other hand, we use their surrounds (i.e., claim, reason, debate context) as another attention vectors to get contextual representations, which work as final clues to select the correct warrant. Our model achieves 60.4% accuracy and ranks 3rd among 22 participating systems.

We present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33%.

To address semantic similarity on multilingual and cross-lingual sentences, we firstly translate other foreign languages into English, and then feed our monolingual English system with various interactive features. Our system is further supported by combining with deep learning semantic similarity and our best run achieves the mean Pearson correlation 73.16% in primary track.

This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on English corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Question-Question Similarity, and subtask C: Question-External Comment Similarity. For subtask A, we combined two different methods to represent question-comment pair, i.e., supervised model using traditional features and Convolutional Neural Network. For subtask B, we utilized the information of snippets returned from Search Engine with question subject as query. For subtask C, we ranked the comments by multiplying the probability of the pair related question comment being Good by the reciprocal rank of the related question.

This paper describes our submissions to task 7 in SemEval 2017, i.e., Detection and Interpretation of English Puns. We participated in the first two subtasks, which are to detect and locate English puns respectively. For subtask 1, we presented a supervised system to determine whether or not a sentence contains a pun using similarity features calculated on sense vectors or cluster center vectors. For subtask 2, we established an unsupervised system to locate the pun by scoring each word in the sentence and we assumed that the word with the smallest score is the pun.

This paper describes our submissions to task 8 in SemEval 2017, i.e., Determining rumour veracity and support for rumours. Given a rumoured tweet and a lot of reply tweets, the subtask A is to label whether these tweets are support, deny, query or comment, and the subtask B aims to predict the veracity (i.e., true, false, and unverified) with a confidence (in range of 0-1) of the given rumoured tweet. For both subtasks, we adopted supervised machine learning methods, incorporating rich features. Since training data is imbalanced, we specifically designed a two-step classifier to address subtask A .

This paper reports our submission to subtask A of task 4 (Sentiment Analysis in Twitter, SAT) in SemEval 2017, i.e., Message Polarity Classification. We investigated several traditional Natural Language Processing (NLP) features, domain specific features and word embedding features together with supervised machine learning methods to address this task. Officially released results showed that our system ranked above average.

This paper describes our systems submitted to the Fine-Grained Sentiment Analysis on Financial Microblogs and News task (i.e., Task 5) in SemEval-2017. This task includes two subtasks in microblogs and news headline domain respectively. To settle this problem, we extract four types of effective features, including linguistic features, sentiment lexicon features, domain-specific features and word embedding features. Then we employ these features to construct models by using ensemble regression algorithms. Our submissions rank 1st and rank 5th in subtask 1 and subtask 2 respectively.

We present a novel multi-task attention based neural network model to address implicit discourse relationship representation and identification through two types of representation learning, an attention based neural network for learning discourse relationship representation with two arguments and a multi-task framework for learning knowledge from annotated and unannotated corpora. The extensive experiments have been performed on two benchmark corpora (i.e., PDTB and CoNLL-2016 datasets). Experimental results show that our proposed model outperforms the state-of-the-art systems on benchmark corpora.

We investigate the task of open domain opinion relation extraction. Different from works on manually labeled corpus, we propose an efficient distantly supervised framework based on pattern matching and neural network classifiers. The patterns are designed to automatically generate training data, and the deep learning model is design to capture various lexical and syntactic features. The result algorithm is fast and scalable on large-scale corpus. We test the system on the Amazon online review dataset. The result shows that our model is able to achieve promising performances without any human annotations.