Thailand

How much information do NLP tasks really need from a transformer&#39;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 (&lt; 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.

IJCNLP-AACL 2021

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

attention sparsity

efficient transformers

self-attention

**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).

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.

workshop paper

Most words are ambiguous––i.e., they convey distinct meanings in different contexts––and even the meanings of unambiguous words are context-dependent. Both phenomena present a challenge for NLP. Recently, the advent of contextualized word embeddings has led to success on tasks involving lexical ambiguity, such as Word Sense Disambiguation. However, there are few tasks that directly evaluate how well these contextualized embeddings accommodate the more continuous, dynamic nature of word meaning––particularly in a way that matches human intuitions. We introduce RAW-C, a dataset of graded, human relatedness judgments for 112 ambiguous words in context (with 672 sentence pairs total), as well as human estimates of sense dominance. The average inter-annotator agreement (assessed using a leave-one-annotator-out method) was 0.79. We then show that a measure of cosine distance, computed using contextualized embeddings from BERT and ELMo, correlates with human judgments, but that cosine distance also systematically underestimates how similar humans find uses of the same sense of a word to be, and systematically overestimates how similar humans find uses of different-sense homonyms. Finally, we propose a synthesis between psycholinguistic theories of the mental lexicon and computational models of lexical semantics.

RAW-C: Relatedness of Ambiguous Words in Context (A New Lexical Resource for English)

Pre-trained language models (LMs) are currently integral to many natural language processing systems. Although multilingual LMs were also introduced to serve many languages, these have limitations such as being costly at inference time and the size and diversity of non-English data involved in their pre-training. We remedy these issues for a collection of diverse Arabic varieties by introducing two powerful deep bidirectional transformer-based models, ARBERT and MARBERT. To evaluate our models, we also introduce ARLUE, a new benchmark for multi-dialectal Arabic language understanding evaluation. ARLUE is built using 42 datasets targeting six different task clusters, allowing us to offer a series of standardized experiments under rich conditions. When fine-tuned on ARLUE, our models collectively achieve new state-of-the-art results across the majority of tasks (37 out of 48 classification tasks, on the 42 datasets). Our best model acquires the highest ARLUE score (77.40) across all six task clusters, outperforming all other models including XLM-R Large (~ 3.4x larger size). Our models are publicly available at https://github.com/UBC-NLP/marbert and ARLUE will be released through the same repository.

ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic

In this work, we introduce a corpus for satire detection in Romanian news. We gathered 55,608 public news articles from multiple real and satirical news sources, composing one of the largest corpora for satire detection regardless of language and the only one for the Romanian language. We provide an official split of the text samples, such that training news articles belong to different sources than test news articles, thus ensuring that models do not achieve high performance simply due to overfitting. We conduct experiments with two state-of-the-art deep neural models, resulting in a set of strong baselines for our novel corpus. Our results show that the machine-level accuracy for satire detection in Romanian is quite low (under 73% on the test set) compared to the human-level accuracy (87%), leaving enough room for improvement in future research.

SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles

Faceted summarization provides briefings of a document from different perspectives. Readers can quickly comprehend the main points of a long document with the help of a structured outline. However, little research has been conducted on this subject, partially due to the lack of large-scale faceted summarization datasets. In this study, we present FacetSum, a faceted summarization benchmark built on Emerald journal articles, covering a diverse range of domains. Different from traditional document-summary pairs, FacetSum provides multiple summaries, each targeted at specific sections of a long document, including the purpose, method, findings, and value. Analyses and empirical results on our dataset reveal the importance of bringing structure into summaries. We believe FacetSum will spur further advances in summarization research and foster the development of NLP systems that can leverage the structured information in both long texts and summaries.

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Multilingual language models have been a crucial breakthrough as they considerably reduce the need of data for under-resourced languages. Nevertheless, the superiority of language-specific models has already been proven for languages having access to large amounts of data. In this work, we focus on Catalan with the aim to explore to what extent a medium-sized monolingual language model is competitive with state-of-the-art large multilingual models. For this, we: (1) build a clean, high-quality textual Catalan corpus (CaText), the largest to date (but only a fraction of the usual size of the previous work in monolingual language models), (2) train a Transformer-based language model for Catalan (BERTa), and (3) devise a thorough evaluation in a diversity of settings, comprising a complete array of downstream tasks, namely, Part of Speech Tagging, Named Entity Recognition and Classification, Text Classification, Question Answering, and Semantic Textual Similarity, with most of the corresponding datasets being created ex novo. The result is a new benchmark, the Catalan Language Understanding Benchmark (CLUB), which we publish as an open resource, together with the clean textual corpus, the language model, and the cleaning pipeline. Using state-of-the-art multilingual models and a monolingual model trained only on Wikipedia as baselines, we consistently observe the superiority of our model across tasks and settings.

Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? {A} Comprehensive Assessment for {C}atalan

Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured at different layers of the model. We investigate how fine-tuning towards downstream NLP tasks impacts the learned linguistic knowledge. We carry out a study across popular pre-trained models BERT, RoBERTa and XLNet using layer and neuron-level diagnostic classifiers. We found that for some GLUE tasks, the network relies on the core linguistic information and preserve it deeper in the network, while for others it forgets. Linguistic information is distributed in the pre-trained language models but becomes localized to the lower layers post fine-tuning, reserving higher layers for the task specific knowledge. The pattern varies across architectures, with BERT retaining linguistic information relatively deeper in the network compared to RoBERTa and XLNet, where it is predominantly delegated to the lower layers.

How transfer learning impacts linguistic knowledge in deep NLP models?

We investigate the semantic knowledge of language models (LMs), focusing on (1) whether these LMs create categories of linguistic environments based on their semantic monotonicity properties, and (2) whether these categories play a similar role in LMs as in human language understanding, using negative polarity item licensing as a case study. 
We introduce a series of experiments consisting of probing with diagnostic classifiers (DCs), linguistic acceptability tasks, as well as a novel DC ranking method that tightly connects the probing results to the inner workings of the LM.
By applying our experimental pipeline to LMs trained on various filtered corpora, we are able to gain stronger insights into the semantic generalizations that are acquired by these models.

Language Models Use Monotonicity to Assess NPI Licensing

Cross-domain slot filling focuses on using la- beled data from source domains to train a slot filling model for target domains. It is of great significance for transferring a dialogue system into new domains. Most of the existing work focused on building a cross-domain transfer model. From the perspective of slots them- selves, this paper proposes a model-agnostic Slot Transferability Measure (STM) for evalu- ating the transferability from a source slot to a target slot, specifically, the degree that labeled data of the source slot is helpful to train the slot filling model for the target slot. We also give a STM-based method for a model to select helpful source slots and their labeled data for a given target slot. Experimental results on mul- tiple existing models and datasets show that our method significantly outperforms state-of- the-art baselines in cross-domain slot filling. The code is available at https://github. com/luhengtong/STM-for-cdsf.git.

Slot Transferability for Cross-domain Slot Filling

Recent papers have introduced methods to incorporate gazetteer features and entity segmentation techniques in neural named entity recognition models. These papers rely on different resources and include features not related to the use of gazetteers, rendering impossible the comparison of the relative effectiveness of the approaches. Here, we provide a comprehensive overview of methods for incorporating gazetteers and for entity segmentation. We evaluate representative methods from each in similar settings for a fair comparison and identify the ones that are consistently better across datasets and input representations. We further show that gazetteers improve entity segmentation and not just entity typing. Hence, we explore their utility in recognizing long entities, a problem for which entity segmentation techniques were developed. Our work explains the mechanisms via which gazetteers improve the performance of neural NER models.

The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English

We introduce a language modeling architecture which operates over sequences of images, or over multimodal sequences of images with associated labels. We use this architecture alongside other embedding models to investigate a category of signs called complex graphemes (CGs) in the undeciphered proto-Elamite script. We argue that CGs have meanings which are at least partly compositional, and we discover novel rules governing the construction of CGs. We find that a language model over sign images produces more interpretable results than a model over text or over sign images and text, which suggests that the names given to signs may be obscuring signals in the corpus. Our results reveal previously unknown regularities in proto-Elamite sign use that can inform future decipherment efforts, and our image-aware language model provides a novel way to abstract away from biases introduced by human annotators.

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

Downloads

Next from IJCNLP-AACL 2021

RAW-C: Relatedness of Ambiguous Words in Context (A New Lexical Resource for English)

Similar lecture

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

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

.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

RAW-C: Relatedness of Ambiguous Words in Context (A New Lexical Resource for English)

Similar lecture

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

Downloads