Taiwan

We introduce a method for analyzing the relationship between internal representations of models and intermediate results by using simple math problems.

IJCNLP-AACL 2022

Tracing and Manipulating Intermediate Results in Neural Math Problem Solvers

intermediate results

math problems

interpretability

neural networks

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

workshop paper

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP).

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
 
 https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

The distinction between mass nouns and count nouns has a long history in formal semantics, and linguists have been trying to identify the semantic properties defining the two classes. However, they also recognized that both can undergo meaning shifts and be used in contexts of a different type, via nominal coercion.
In this study, we present an approach to measure the meaning shift in count-mass coercion in English that makes use of static and contextualized word embedding distance. Our results show that the coercion shifts are detected only by a small subset of the traditional word embedding models and that the shifts detected by the contextualized embedding of BERT are more pronounced for mass nouns.

Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings.

In this presentation, we introduce a new approach that simulates the construction of phrasal meaning as an analogical process implemented with deep learning techniques. We propose a distributional representation of constructional phrases (namely Relational Embeddings) and a neural network model for generating new embeddings analogically rather than applying traditional compositional operations, which we call ANNE (Analogical Neural Network for Embeddings). 
We experimented with our analogical neural network to understand how it can generalize and be extendable to different scenarios. We argued that the proposed methodology could open the doors to new analyses in distributional semantics as well as in computational models of language processing.

Compositionality as an Analogical Process: Introducing ANNE.


We present a Japanese morphological corpus of sentences from 27 specialized domains for the two tasks of word segmentation and partof-speech tagging. Experiments on the corpus demonstrated that recent neural models with domain adaptation techniques and pretrained language models achieved accurate performance for the two tasks for many specialized domains

A Japanese Corpus of Many Specialized Domains for Word Segmentation and Part-of-Speech Tagging

Transformer-based language models are often trained on structured text where non-lexical markers of sentence and discourse structure (e.g., punctuation and casing) are present and used consistently. Transformers encode these markers and arguably benefit from the information they convey. Yet, a systematic evaluations of the contribution of non-lexical markers to model performance, and of whether models' behavior changes significantly in their absence, is currently lacking. This knowledge is both relevant from a theoretical standpoint, but also important to understand how well pretrained models may perform in common application scenarios where casing and punctuation are absent or inconsistent. 
Here, we analyze GPT-2's language modeling behavior in parallel corpora that differ in the presence vs. absence of consistent punctuation and casing. We compute GPT-2's precision and uncertainty in next-token prediction for multiple context sizes, and compare the resulting performance distributions across corpora. We find that absence of non-lexical markers, especially punctuation, increases model uncertainty, and it affects (but does not catastrophically disrupt) GPT-2's precision in next-token prediction. Interestingly, the absence of non-lexical markers prevents the model from benefiting from larger contexts in order to reduce the uncertainty of its predictions. Future work will extend this paradigm to a wider range of models and systematically investigate how features of training text affect both language modeling and downstream predictive performance.

Evaluating the role of non-lexical markers in GPT-2’s language modeling behavior

From COMET to COMES – Can Summary Evaluation Benefit from Translation Evaluation?

Random Text Perturbations Work, but not Always

A Comparative Analysis of Stance Detection Approaches and Datasets

Determining the origin of a given passage in rabbinic ontologies such as medieval midrash collections is not always straightforward and is often a matter of dispute among scholars, yet it is essential for scholars' understanding of the passage and its relationship to other texts in the rabbinic corpus. 

To help solve this problem, we propose a system for classification of rabbinic literature based on its style, leveraging recently released pretrained Transformer models for Hebrew. By combining our model with a text reuse engine, we demonstrate how our method can be applied to uncover lost material from the Tanhuma-Yelammedenu literature.

Style Classification of Rabbinic Literature for Detection of Lost Midrash Tanhuma Material

Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of- art performance across tasks in text processing. Data Augmentation techniques have also helped build state-of-art models on low or zero resource tasks. Many works in the past have attempted at learning a single massively- multilingual machine translation model for zero-shot translation. Although those translation models are producing correct translations, the main challenge is those models are producing the wrong languages for zero-shot translation. This work and its results indicate that prompt conditioned large models do not suffer from off-target language errors i.e. errors arising due to translation to wrong languages. We empirically demonstrate the effectiveness of self-supervised pre-training and data augmentation for zero-shot multi-lingual machine translation.

MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation

Recent studies have reported that neural reasoning improves its accuracy when generating the intermediate reasoning steps. However, it is yet unclear what factors lead to such benefits.
We investigate and factorize the benefit of generating intermediate steps for symbolic reasoning.
Specifically, we decomposed the reasoning strategy regarding step granularity and chaining strategy. 
With a purely symbolic numerical reasoning dataset (e.g., A=1, B=3, C=A+3, C?), we found that the choice of reasoning strategies significantly affects the performance, with the gap becoming even larger as the extrapolation length becomes longer.
Surprisingly, we also found that certain configurations lead to nearly perfect performance, even in the case of length extrapolation.
Our results indicate the importance of further exploring effective strategies for neural reasoning models.

Tracing and Manipulating Intermediate Results in Neural Math Problem Solvers

Downloads

Next from IJCNLP-AACL 2022

Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings.

Similar lecture

Approximate Nearest Neighbour Extraction Techniques and Neural Networks \\for Suicide Risk Prediction in the CLPsych 2022 Shared Task

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Tracing and Manipulating Intermediate Results in Neural Math Problem Solvers

.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 2022

Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings.

Similar lecture

Approximate Nearest Neighbour Extraction Techniques and Neural Networks \\for Suicide Risk Prediction in the CLPsych 2022 Shared Task

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads