Thailand

IJCNLP-AACL 2021

Pre-training Methods for Neural Machine Translation - Part 1 and 2

**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).

tutorial

Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervision, which often results in instability and makes the model easily collapsed. In this paper, we revisit the procedure of OpenRE from a causal view. By formulating OpenRE using a structural causal model, we identify that the above-mentioned problems stem from the spurious correlations from entities and context to the relation type. To address this issue, we conduct \emph{Element Intervention}, which intervene on the context and entities respectively to obtain the underlying causal effects of them. We also provide two specific implementations of the interventions based on entity ranking and context contrasting. Experimental results on unsupervised relation extraction datasets show our method to outperform previous state-of-the-art methods and is robust across different datasets.

Element Intervention for Open Relation Extraction

Automatic extraction of product attribute values is an important enabling technology in e-Commerce platforms. This task is usually modeled using sequence labeling architectures, with several extensions to handle multi-attribute extraction. One line of previous work constructs attribute-specific models, through separate decoders or entirely separate models. However, this approach constrains knowledge sharing across different attributes. Other contributions use a single multi-attribute model, with different techniques to embed attribute information. But sharing the entire network parameters across all attributes can limit the model's capacity to capture attribute-specific characteristics. In this paper we present AdaTag, which uses adaptive decoding to handle extraction. We parameterize the decoder with pretrained attribute embeddings, through a hypernetwork and a Mixture-of-Experts (MoE) module. This allows for separate, but semantically correlated, decoders to be generated on the fly for different attributes. This approach facilitates knowledge sharing, while maintaining the specificity of each attribute. Our experiments on a real-world e-Commerce dataset show marked improvements over previous methods.

AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding

With the rapid development of NLP research, leaderboards have emerged as one tool to track the performance of various systems on various NLP tasks. They are effective in this goal to some extent, but generally present a rather simplistic one-dimensional view of the submitted systems, communicated only through holistic accuracy numbers. In this paper, we present a new conceptualization and implementation of NLP evaluation: the \textsc{ExplainaBoard}, which in addition to inheriting the functionality of the standard leaderboard, also allows researchers to (i) diagnose strengths and weaknesses of a single system (e.g.~what is the best-performing system bad at?) (ii) interpret relationships between multiple systems. (e.g.~where does system \texttt{A} outperform system \texttt{B}? What if we combine systems \texttt{A}, \texttt{B} and \texttt{C}?) and (iii) examine prediction results closely (e.g.~what are common errors made by multiple systems, or in what contexts do particular errors occur?). 
So far, \textsc{ExplainaBoard} covers more than 400 systems, 50 datasets, 40 languages, and 12 tasks.
We not only released an online \textbf{platform} 
but also make our evaluation tool an \textbf{API} with \textit{MIT Licence} at Github
and PyPi that allows users to conveniently assess their models offline. We additionally release all \textbf{output files} from systems that we have run or collected to motivate ``output-driven'' research in the future.


ExplainaBoard: An Explainable Leaderboard for NLP

We present TweeNLP, a one-stop portal that organizes Twitter’s natural language processing (NLP) data and builds a visualization and exploration platform. It curates 19,395 tweets (as of April 2021) from various NLP conferences and general NLP discussions. It supports multiple features such as TweetExplorer to explore tweets by topics, visualize insights from Twitter activity throughout the organization cycle of conferences, discover popular research papers and researchers. It also builds a timeline of conference and workshop submission deadlines. We envision TweeNLP to function as a collective memory unit for the NLP community by integrating the tweets pertaining to research papers with the NLPExplorer scientific literature search engine. The current system is hosted at http://nlpexplorer.org/twitter/CFP.

TweeNLP: A Twitter Exploration Portal for Natural Language Processing

A natural language database interface (NLDB) can democratize data-driven insights for non-technical users. However, existing Text-to-SQL semantic parsers cannot achieve high enough accuracy in the cross-database setting to allow good usability in practice. This work presents Turing, a NLDB system toward bridging this gap.
The cross-domain semantic parser of Turing with our novel value prediction method achieves 75.1% execution accuracy, and 78.3% top-5 beam execution accuracy on the Spider validation set. To benefit from the higher beam accuracy, we design an interactive system where the SQL hypotheses in the beam are explained step-by-step in natural language, with their differences highlighted. The user can then compare and judge the hypotheses to select which one reflects their intention if any. The English explanations of SQL queries in Turing are produced by our high-precision natural language generation system based on synchronous grammars.


TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface

Memes are the combinations of text and images that are often humorous in nature. But, that may not always be the case and certain combinations of texts and images may depict hate, referred to as hateful memes. This work presents a multimodal pipeline that takes both visual and textual features from memes into account to (1) identify the protected category (e.g. race, sex etc.) that has been attacked and (2) detect the type of attack (e.g. contempt, slurs etc.). Our pipeline utilizes state-of-the-art pre-trained visual and textual representations, followed by a simple logistic regression classifier. We employ our pipeline on the Hateful Memes Challenge dataset with additional newly created fine-grained labels for protected category and type of attack. Our best model achieves an AUROC of 0.96 for identifying protected category, and 0.97 for detecting the type of attack. We release our code at https://github.com/harisbinzia/HatefulMemes.

Racist or Sexist Meme? Classifying Memes beyond Hateful

The Shared Task on Hateful Memes is a challenge that aims at the detection of hateful content in memes by inviting the implementation of systems that understand memes, potentially by combining image and textual information. The challenge consists of three detection tasks: hate, protected category and attack type. The first is a binary classification task, while the other two are multi-label classification tasks. Our participation included a text-based BERT baseline (TxtBERT), the same but adding information from the image (ImgTxtBERT), and neural retrieval approaches. We also experimented with retrieval augmented classification models. We find that an ensemble of TxtBERT and ImgBERT achieves the best performance in two out of the three tasks.

Pre-training Methods for Neural Machine Translation - Part 1 and 2

Downloads

Next from IJCNLP-AACL 2021

Element Intervention for Open Relation Extraction

Similar lecture

Alpha at SemEval-2021 Tasks 6: Transformer Based Propaganda Classification

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Pre-training Methods for Neural Machine Translation - Part 1 and 2

.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 IJCNLP-AACL 2021

Element Intervention for Open Relation Extraction

Similar lecture

Alpha at SemEval-2021 Tasks 6: Transformer Based Propaganda Classification

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads