Dominican Republic

Intermediate task fine-tuning has been shown to culminate in large transfer gains across many NLP tasks. With an abundance of candidate datasets as well as pre-trained language models, it has become infeasible to run the cross-product of all combinations to find the best transfer setting. In this work we first establish that similar sequential fine-tuning gains can be achieved in adapter settings, and subsequently consolidate previously proposed methods that efficiently identify beneficial tasks for intermediate transfer learning. We experiment with a diverse set of 42 intermediate and 11 target English classification, multiple choice, question answering, and sequence tagging tasks. Our results show that efficient embedding based methods that rely solely on the respective datasets outperform computational expensive few-shot fine-tuning approaches. Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training.

EMNLP 2021

What to Pre-Train on? Efficient Intermediate Task Selection

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

technical paper

Discontinuous constituent parsers have always lagged behind continuous approaches in terms of accuracy and speed, as the presence of constituents with discontinuous yield introduces extra complexity to the task. However, a discontinuous tree can be converted into a continuous variant by reordering tokens. Based on that, we propose to reduce discontinuous parsing to a continuous problem, which can then be directly solved by any off-the-shelf continuous parser. To that end, we develop a Pointer Network capable of accurately generating the continuous token arrangement for a given input sentence and define a bijective function to recover the original order. Experiments on the main benchmarks with two continuous parsers prove that our approach is on par in accuracy with purely discontinuous state-of-the-art algorithms, but considerably faster.

Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering

Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces.

Extracting Event Temporal Relations via Hyperbolic Geometry

The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are used. In this work, we investigate the compatibility of tokenizations for multilingual static and contextualized embedding spaces and propose a measure that reflects the compatibility of tokenizations across languages. Our goal is to prevent incompatible tokenizations, e.g., "wine" (word-level) in English vs. "v i n" (character-level) in French, which make it hard to learn good multilingual semantic representations. We show that our compatibility measure allows the system designer to create vocabularies across languages that are compatible -- a desideratum that so far has been neglected in multilingual models.

Wine is not v i n. On the Compatibility of Tokenizations across Languages

Both word-level noise and sentence-level noise are challenges for Distantly Supervised Relation Extraction (DSRE). In this presentation, we introduce our novel Multi-Layer Revision Network (MLRN) which alleviates word-level noise by emphasizing inner-sentence correlations before extracting relevant information within sentences. We also devise a balanced and noise-resistant Confidence-based Multi-Instance Learning (CMIL) method which combines hard filtering and soft weighting to address sentence-level noise. Experiments show that our approach achieves significant improvements over the baselines.

Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance Learning

Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly understood how neural networks change after fine-tuning. In this work, we use centered kernel alignment (CKA), a method for comparing learned representations, to measure the similarity of representations in task-tuned models across layers. In experiments across twelve NLU tasks, we discover a consistent block diagonal structure in the similarity of representations within fine-tuned RoBERTa and ALBERT models, with strong similarity within clusters of earlier and later layers, but not between them. The similarity of later layer representations implies that later layers only marginally contribute to task performance, and we verify in experiments that the top few layers of fine-tuned Transformers can be discarded without hurting performance, even with no further tuning.

Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers

Existing techniques for mitigating dataset bias often leverage a biased model to identify biased instances. The role of these biased instances is then reduced during the training of the main model to enhance its robustness to out-of-distribution data. A common core assumption of these techniques is that the main model handles biased instances similarly to the biased model, in that it will resort to biases whenever available. In this paper, we show that this assumption does not hold in general. We carry out a critical investigation on two well-known datasets in the domain, MNLI and FEVER, along with two biased instance detection methods, partial-input and limited-capacity models. Our experiments show that in around a third to a half of instances, the biased model is unable to predict the main model's behavior, highlighted by the significantly different parts of the input on which they base their decisions. Based on a manual validation, we also show that this estimate is highly in line with human interpretation. Our findings suggest that down-weighting of instances detected by bias detection methods, which is a widely-practiced procedure, is an unnecessary waste of training data. We release our code to facilitate reproducibility and future research.

Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques

Pre-trained language-vision models have
shown remarkable performance on the visual
question answering (VQA) task. However,
most of the pre-trained models are trained
by only considering monolingual learning,
especially the resource-rich language like
English. Training such models for multilingual setups demand high computing resources and multilingual language-vision dataset
which hinders their application in practice.
To alleviate these challenges, we propose a
knowledge distillation approach to extend
an English language-vision model (teacher)
into an equally effective multilingual and
code-mixed model (student). Different from
the existing knowledge distillation methods,
which only use the output from the last layer
of the teacher network for distillation, our
student model learns and imitates the teacher
from multiple intermediate layers (language
and vision encoders) with appropriately
design distillation objectives for incremental
knowledge extraction. We also create the
large-scale multilingual and code-mixed
VQA dataset in eleven different language
setups considering the multiple Indian and
European languages. Experimental results and
in-depth analysis shows the effectiveness of
the proposed VQA model over the pre-trained
language-vision models on eleven diverse
language setups.

Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation

Transformer-based pre-training techniques of text and layout have proven effective in a number of document understanding tasks. Despite this success, multimodal pre-training models suffer from very high computational and memory costs. Motivated by human reading strategies, this paper presents Skim-Attention, a new attention mechanism that takes advantage of the structure of the document and its layout. Skim-Attention only attends to the 2-dimensional position of the words in a document. Our experiments show that Skim-Attention obtains a lower perplexity than prior works, while being more computationally efficient. Skim-Attention can be further combined with long-range Transformers to efficiently process long documents. We also show how Skim-Attention can be used off-the-shelf as a mask for any Pre-trained Language Model, allowing to improve their performance while restricting attention. Finally, we show the emergence of a document structure representation in Skim-Attention.

Skim-Attention: Learning to Focus via Document Layout

The lexical substitution task aims at generating a list of suitable replacements for a target word in context, ideally keeping the meaning of the modified text unchanged. While its usage has increased in recent years, the paucity of annotated data prevents the finetuning of neural models on the task, hindering the full fruition of recently introduced powerful architectures such as language models. Furthermore, lexical substitution is usually evaluated in a framework that is strictly bound to a limited vocabulary, making it impossible to credit appropriate, but out-of-vocabulary, substitutes. To assess these issues, we propose GeneSis (Generating Substitutes in contexts), the first generative approach to lexical substitution. Thanks to a seq2seq model, we generate substitutes for a word according to the context it appears in, attaining state-of-the-art results on different benchmarks. Moreover, our approach allows silver data to be produced for further improving the performances of lexical substitution systems. Along with an extensive analysis of GeneSis results, we also present a human evaluation of the generated substitutes in order to assess their quality. We release the fine-tuned models, the generated datasets and the code to reproduce the experiments at https://github. com/SapienzaNLP/genesis.

GeneSis: A Generative Approach to Substitutes in Context

Asking questions about a situation is an inherent step towards understanding it. 
To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of questions asking about all possible semantic roles of the predicate. We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage.
Unlike most existing approaches to question generation, our approach does not require conditioning on existing answers in the text.
Instead, we condition on the type of information to inquire about, regardless of whether the answer appears explicitly in the text, could be inferred from it, or should be sought elsewhere.
Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.

What to Pre-Train on? Efficient Intermediate Task Selection

Downloads

Next from EMNLP 2021

Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering

Similar lecture

Language, Brains & Interpretability