Thailand

Chinese spelling correction (CSC) is an important yet challenging task. Existing state-of-the-art methods either only use a pre-trained language model or incorporate phonological information as external knowledge. In this paper, we propose a novel end-to-end CSC model that integrates phonetic features into language model by leveraging the powerful pre-training and fine-tuning method. Instead of conventionally masking words with a special token in training language model, we replace words with phonetic features and their sound-alike words. We further propose an adaptive weighted objective to jointly train error detection and correction in a unified framework. Experimental results show that our model achieves significant improvements on SIGHAN datasets and 
outperforms the previous state-of-the-art methods.

IJCNLP-AACL 2021

Correcting Chinese Spelling Errors with Phonetic Pre-training

phonetic features

spelling error correction

pre-training

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

technical paper

Automatic dialogue coherence evaluation has attracted increasing attention and is crucial for developing promising dialogue systems.
However, existing metrics have two major limitations:
(a) they are mostly trained in a simplified two-level setting (coherent vs. incoherent), while humans give Likert-type multi-level coherence scores, dubbed as "quantifiable"; (b) their predicted coherence scores cannot align with the actual human rating standards due to the absence of human guidance during training. To address these limitations, we propose Quantifiable Dialogue Coherence Evaluation (QuantiDCE), a novel framework aiming to train a quantifiable dialogue coherence metric that can reflect the actual human rating standards. Specifically, QuantiDCE includes two training stages, Multi-Level Ranking (MLR) pre-training and Knowledge Distillation (KD) fine-tuning. During MLR pre-training, a new MLR loss is proposed for enabling the model to learn the coarse judgement of coherence degrees. Then, during KD fine-tuning, the pretrained model is further finetuned to learn the actual human rating standards with only very few human-annotated data. To advocate the generalizability even with limited fine-tuning data, a novel KD regularization is introduced to retain the knowledge learned at the pre-training stage. Experimental results show that the model trained by QuantiDCE presents stronger correlations with human judgements than the other state-of-the-art metrics.

Towards Quantifiable Dialogue Coherence Evaluation

Ordinal Classification (OC) is an important classification task where the classes are ordinal. For example, an OC task for sentiment analysis could have the following classes: highly positive, positive, neutral, negative, highly negative. Clearly, evaluation measures for an OC task should penalise misclassifications by considering the ordinal nature of the classes. Ordinal Quantification (OQ) is a related task where the gold data is a distribution over ordinal classes, and the system is required to estimate this distribution. Evaluation measures for an OQ task should also take the ordinal nature of the classes into account. However, for both OC and OQ, there are only a small number of known evaluation measures that meet this basic requirement. In the present study, we utilise data from the SemEval and NTCIR communities to clarify the properties of nine evaluation measures in the context of OC tasks, and six measures in the context of OQ tasks.

Evaluating Evaluation Measures for Ordinal Classification and Ordinal Quantification

High-quality alignment between movie scripts and plot summaries is an asset for learning to summarize stories and to generate dialogues. The alignment task is challenging as scripts and summaries substantially differ in details and abstraction levels as well as in linguistic register.
This paper addresses the alignment problem by devising a fully unsupervised approach based on a global optimization model. Experimental results on ten movies show the viability of our method with 76% F1-score and its superiority over a previous baseline. We publish alignments for 914 movies to foster research in this new topic.

AligNarr: Aligning Narratives on Movies

Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many annotated resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embeddings of noisy attribute values by inter-attribute attention with unlabeled data. Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts. Experiments on 6 public datasets and 3 industrial datasets show that our method is highly efficient and outperforms SOTA EM models in most cases. We will release the codes upon acceptance.

Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

A summary quality measure is judged by how well it correlates with quality scores produced by human annotators. A higher correlation with human scores is considered to be a decisive indicator of a better measure. In this work we present observations that cast doubt on this view. We also show a possibility of an alternative indicator for selecting the best measure from a family of measures, a criterion that does not rely on human scores.

Is Human Scoring the Best Criteria for Summary Evaluation?

An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems. Existing automatic evaluation metrics are based on turn-level quality evaluation and use average scores for system-level comparison. In this paper, we propose to measure the performance of a dialogue system by computing the distribution-wise distance between its generated conversations and real-world conversations. Specifically, two distribution-wise metrics, FBD and PRD, are developed and evaluated. Experiments on several dialogue corpora show that our proposed metrics correlate better with human judgments than existing metrics.

Assessing Dialogue Systems with Distribution Distances

We propose two fast neural combinatory models for constituency parsing: binary and multi-branching. Our models decompose the bottom-up parsing process into 1) classification of tags, labels, and binary orientations or chunks and 2) vector composition based on the computed orientations or chunks. These models have theoretical sub-quadratic complexity and empirical linear complexity. The binary model achieves an F1 score of 92.54 on Penn Treebank, speeding at 1327.2 sents/sec. Both the models with XLNet provide near state-of-the-art accuracies for English. Syntactic branching tendency and headedness of a language are observed during the training and inference processes for Penn Treebank, Chinese Treebank, and Keyaki Treebank (Japanese).

Neural Combinatory Constituency Parsing

Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data and its end-to-end models incompatible with their ST counterparts. In observation of this obstacle, we propose to bridge this representation gap with Chimera. By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new stateof-the-art. Specifically, Chimera obtains 27.1 BLEU on MuST-C ENDE, improving the SOTA by a +1.9 BLEU margin. Further experimental analyses demonstrate that shared semantic space indeed conveys common knowledge between these two tasks and thus paves a new way for augmenting training resources across modalities.

Learning Shared Semantic Space for Speech-to-Text Translation

Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning. However, existing methods indiscriminately use the recognized patterns in the testing phase that is inherently different from us humans who have counterfactual thinking, e.g., to scrutinize for the hard testing samples. Inspired by this, we propose a Counterfactual Reasoning Model, which mimics the counterfactual thinking by learning from few counterfactual samples. In particular, we devise a generation module to generate representative counterfactual samples for each factual sample, and a retrospective module to retrospect the model prediction by comparing the counterfactual and factual samples. Extensive experiments on sentiment analysis (SA) and natural language inference (NLI) validate the effectiveness of our method.

Empowering Language Understanding with Counterfactual Reasoning

Machine Reading Comprehension (MRC) aims to extract answers to questions given a passage, 
which has been widely studied recently especially in open domains. 
However, few efforts have been made on closed-domain MRC, mainly due to the lack of large-scale training data. In this paper, we introduce a multi-target MRC task for the medical domain, whose goal is to predict answers to medical questions and the corresponding support sentences from medical information sources simultaneously, in order to ensure the high reliability of medical knowledge serving. A high-quality dataset more than 18k samples) is manually constructed for the purpose, named Multi-task Chinese Medical MRC dataset (CMedMRC), with detailed analysis conducted. We further propose a Chinese medical BERT model for the task (CMedBERT), which fuses medical knowledge into pre-trained language models by the dynamic fusion mechanism of heterogeneous features and the multi-task learning strategy.
Experiments show that CMedBERT consistently outperforms strong baselines by fusing context-aware and knowledge-aware token representations.

Correcting Chinese Spelling Errors with Phonetic Pre-training

Downloads

Next from IJCNLP-AACL 2021

Towards Quantifiable Dialogue Coherence Evaluation

Similar lecture

Investigating Toxic Span Detection Using RoBERTa Pre-training