Thailand

emi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels and train the deep classifier over the mixture of labeled and pseudo-labeled texts. Naturally, their performance is largely affected by the accuracy of pseudo-labels for unlabeled texts. Unfortunately, they often suffer from low accuracy because of the margin bias problem caused by the large difference between representation distributions of labels in SSTC. To alleviate this problem, we apply the angular margin loss, and perform Gaussian linear transformation to achieve balanced label angle variances, i.e., the variance of label angles of texts within the same label. More accuracy of predicted pseudo-labels can be achieved by constraining all label angle variances balanced, where they are estimated over both labeled and pseudo-labeled texts during self-training loops. With this insight, we propose a novel SSTC method, namely Semi-Supervised Text Classification with Balanced Deep representation Distributions (S2TC-BDD). To evaluate S2TC-BDD, we compare it against the state-of-the-art SSTC methods. Empirical results demonstrate the effectiveness of S2TC-BDD, especially when the labeled texts are scarce.

ACL-IJCNLP 2021

Semi-Supervised Text Classification with Balanced Deep Representation Distributions

balanced deep representation distributions

semi-supervised text classification

self-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

Hierarchical Text Classification (HTC) is a challenging task that categorizes a textual description within a taxonomic hierarchy. Most of the existing methods focus on modeling the text. Recently, researchers attempt to model the class representations with some resources (e.g., external dictionaries). However, the concept shared among classes which is a kind of domain-specific and fine-grained information has been ignored in previous work. In this paper, we propose a novel concept-based label embedding method that can explicitly represent the concept and model the sharing mechanism among classes for the hierarchical text classification. Experimental results on two widely used datasets prove that the proposed model outperforms several state-of-the-art methods. We release our complementary resources (concepts and definitions of classes) for these two datasets to benefit the research on HTC.

Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification

Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In this paper, we propose VisualSparta, a novel (Visual-text Sparse Transformer Matching) model that shows significant improvement in terms of both accuracy and efficiency. VisualSparta is capable of outperforming previous state-of-the-art scalable methods in MSCOCO and Flickr30K. We also show that it achieves substantial retrieving speed advantages, i.e., for a 1 million image index, VisualSparta using CPU gets ~391X speedup compared to CPU vector search and ~5.4X speedup compared to vector search with GPU acceleration. Experiments show that this speed advantage even gets bigger for larger datasets because VisualSparta can be efficiently implemented as an inverted index. To the best of our knowledge, VisualSparta is the first transformer-based text-to-image retrieval model that can achieve real-time searching for large-scale datasets, with significant accuracy improvement compared to previous state-of-the-art methods.

VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words

The effectiveness of Neural Information Retrieval (Neu-IR) often depends on a large scale of in-domain relevance training signals, which are not always available in real-world ranking scenarios. To democratize the benefits of Neu-IR, this paper presents MetaAdaptRank, a domain adaptive learning method that generalizes Neu-IR models from label-rich source domains to few-shot target domains. Drawing on source-domain massive relevance supervision, MetaAdaptRank contrastively synthesizes a large number of weak supervision signals for target domains and meta-learns to reweight these synthetic "weak" data based on their benefits to the target-domain ranking accuracy of Neu-IR models. Experiments on three TREC benchmarks in the web, news, and biomedical domains show that MetaAdaptRank significantly improves the few-shot ranking accuracy of Neu-IR models. Further analyses indicate that MetaAdaptRank thrives from both its contrastive weak data synthesis and meta-reweighted data selection. The code and data of this paper can be obtained from https://github.com/thunlp/MetaAdaptRank.

Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision

How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)?
From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can be discretized to fewer values with minimal loss to task accuracies. 
However, this requires retraining or even creating entirely new models, both of which can be expensive and carbon-emitting. 
Focused on optimizations that do not require training, we systematically study the full range of typical attention values necessary. 
This informs the design of an inference-time quantization technique using both pruning and log-scaled mapping which produces only a few (e.g. $2^3$) unique values. 
Over the tasks of question answering and sentiment analysis, we find nearly 80\% of attention values can be pruned to zeros with minimal ($< 1.0\%$) relative loss in accuracy. 
We use this pruning technique in conjunction with quantizing the attention values to only a 3-bit format, without retraining, resulting in only a 0.8\% accuracy reduction on question answering with fine-tuned RoBERTa.

On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers

Is it possible to use natural language to intervene in a model’s behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the context of social stereotypes. Specifically, we propose a new language understanding task, Linguistic Ethical Interventions (LEI), where the goal is to amend a question-answering (QA) model’s unethical behavior by communicating context-specific principles of ethics and equity to it. To this end, we build upon recent methods for quantifying a system’s social stereotypes, augmenting them with different kinds of ethical interventions and the desired model behavior under such interventions. Our zero-shot evaluation finds that even today’s powerful neural language models are extremely poor ethical-advice takers, that is, they respond surprisingly little to ethical interventions even though these interventions are stated as simple sentences. Few-shot learning improves model behavior but remains far from the desired outcome, especially when evaluated for various types of generalization. Our new task thus poses a novel language understanding challenge for the community.

Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?

Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit. Large pretrained language models (PLMs) can achieve near-human performance on such tasks, while providing little human-interpretable evidence of the underlying reasoning they use. In this work, we show how to use these same models to generate such evidence: inspired by the contrastive nature of human explanations, we use PLMs to complete explanation prompts which contrast alternatives according to the key attribute(s) required to justify the correct answer (for example, peanuts are usually salty while raisins are sweet). Conditioning model decisions on these explanations improves performance on two commonsense reasoning benchmarks, as compared to previous non-contrastive alternatives. These explanations are also judged by humans to be more relevant for solving the task, and facilitate a novel evaluation of explanation faithfulness.

Prompting Contrastive Explanations for Commonsense Reasoning Tasks

The drastic decrease in mobile SMS costs turned phone users more prone to spam messages, usually with unwanted marketing or questionable content. As such, researchers have proposed different methods for detecting SMS spam messages. This paper presents a technique for embedding SMS messages into vector spaces that is suitable for spam detection. The proposed approach relies on mining patterns that are relevant for distinguishing spam from legitimate messages. A subset of those patterns is used to construct a function that maps text messages into a multidimensional vector space. The extracted patterns are represented as skip-grams of token attributes, where a skip-gram can be seen as a generalization of the n-gram model that allows a distance greater than one between matched tokens in the text. We evaluate the proposed approach using the generated vectors for spam classification on the UCI Spam Collection dataset. The experiments showed that our method combined with shallow networks reached accuracy that is competitive with some state-of-the-art approaches.

SMS Spam Detection Through Skip-gram Embeddings and Shallow Networks

Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation between verbs and arguments in isolation, in this paper we take a broader perspective by assessing whether and to what extent computational approaches have access to the information about the typicality of entire events and situations described in language (Generalized Event Knowledge).
Given the recent success of Transformers Language Models (TLMs), we decided to test them on a benchmark for the dynamic estimation of thematic fit. The evaluation of these models was performed in comparison with SDM, a framework specifically designed to integrate events in sentence meaning representations, and we conducted a detailed error analysis to investigate which factors affect their behavior. Our results show that TLMs can reach performances that are comparable to those
achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge, and their predictions often depend on surface linguistic features, such as frequent words, collocations and syntactic patterns, thereby showing sub-optimal generalization abilities.

Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge

Abstract Meaning Representation (AMR) is a sentence-level meaning representation based on predicate argument structure. One of the challenges we find in AMR parsing is to capture the structure of complex sentences which expresses the relation between predicates. Knowing the core part of the sentence structure in advance may be beneficial in such a task. In this paper, we present a list of dependency patterns for English complex sentence constructions designed for AMR parsing. With a dedicated pattern matcher, all occurrences of complex sentence constructions are retrieved from an input sentence. While some of the subordinators have semantic ambiguities, we deal with this problem through training classification models on data derived from AMR and Wikipedia corpus, establishing a new baseline for future works. The developed complex sentence patterns and the corresponding AMR descriptions will be made public.

Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing

The paper reports on a corpus study of German light verb constructions (LVCs). LVCs come in families which exemplify systematic interpretation patterns. The paper's aim is to account for the properties determining these patterns on the basis of a corpus study on German LVCs of the type 'stehen unterNP' ('stand under NP').

Semi-Supervised Text Classification with Balanced Deep Representation Distributions

Downloads

Next from ACL-IJCNLP 2021

Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification

Similar lecture

The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation

Semi-Supervised Text Classification with Balanced Deep Representation Distributions

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL-IJCNLP 2021

Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification

Similar lecture

The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation

Downloads