Dominican Republic

We propose a rolling version of the Latent Dirichlet Allocation, called RollingLDA. By a sequential approach, it enables the construction of LDA-based time series of topics that are consistent with previous states of LDA models. After an initial modeling, updates can be computed efficiently, allowing for real-time monitoring and detection of events or structural breaks. For this purpose, we propose suitable similarity measures for topics and provide simulation evidence of superiority over other commonly used approaches. The adequacy of the resulting method is illustrated by an application to an example corpus. In particular, we compute the similarity of sequentially obtained topic and word distributions over consecutive time periods. For a representative example corpus consisting of The New York Times articles from 1980 to 2020, we analyze the effect of several tuning parameter choices and we run the RollingLDA method on the full dataset of approximately 4 million articles to demonstrate its feasibility.

EMNLP 2021

{RollingLDA}: {A}n Update Algorithm of Latent {D}irichlet Allocation to Construct Consistent Time Series from Textual Data

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

Existing unsupervised document hashing methods are mostly established on generative models. Due to the difficulties of capturing long dependency structures, these methods rarely model the raw documents directly, but instead to model the features extracted from them ({\it e.g.} bag-of-words (BOG), TFIDF). In this paper, we propose to learn hash codes from BERT embeddings after observing their tremendous successes on downstream tasks. As a first try, we modify existing generative hashing models to accommodate the BERT embeddings. However, little improvement is observed over the codes learned from the old BOG or TFIDF features. We attribute this to the reconstruction requirement in the generative hashing, which will enforce irrelevant information that is abundant in the BERT embeddings also compressed into the codes. To remedy this issue, a new unsupervised hashing paradigm is further proposed based on the mutual information (MI) maximization principle. Specifically, the method first constructs appropriate global and local codes from the documents and then seeks to maximize their mutual information. Experimental results on three benchmark datasets demonstrate that the proposed method is able to generate hash codes that outperform existing ones learned from BOG features by a substantial margin.

Refining BERT Embeddings for Document Hashing via Mutual Information Maximization

Robust sequence-to-sequence modelling is an essential task in the real world where the inputs are often noisy. Both user-generated and machine generated inputs contain various kinds of noises in the form of spelling mistakes, grammatical errors, character recognition errors, all of which impact downstream tasks and affect interpretability of texts. In this work, we devise a novel sequence-to-sequence architecture for detecting and correcting different real world and artificial noises (adversarial attacks) from English texts. Towards that we propose a modified Transformer-based encoder-decoder architecture that uses a gating mechanism to detect types of corrections required and accordingly corrects texts. Experimental results show that our gated architecture with pre-trained language models perform significantly better that the non-gated counterparts and other state-of-the-art error correction models in correcting spelling and grammatical errors. Extrinsic evaluation of our model on Machine Translation (MT) and Summarization tasks show the competitive performance of the model against other generative sequence-to-sequence models under noisy inputs.

{G}ated {T}ransformer for {R}obust {D}e-noised {S}equence-to-{S}equence {M}odelling

Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.

Contrastive Document Representation Learning with Graph Attention Networks

Natural language processing (NLP) is often the backbone of today's systems for user interactions, information retrieval and others. Many of such NLP applications rely on specialized learned representations (e.g. neural word embeddings, topic models) that improve the ability to reason about the relationships between documents of a corpus. Paired with the progress in learned representations, the similarity metrics used to compare representations of documents are also evolving, with numerous proposals differing in computation time or interpretability. In this paper we propose an extension to a specific emerging hybrid document distance metric which combines topic models and word embeddings: the Hierarchical Optimal Topic Transport (HOTT). In specific, we extend HOTT by using context-enhanced word representations. We provide a validation of our approach on public datasets, using the language model BERT for a document categorization task. Results indicate competitive performance of the extended HOTT metric. We furthermore apply the HOTT metric and its extension to support educational media research, with a retrieval task of matching topics in German curricula to educational textbooks passages, along with offering an auxiliary explanatory document representing the dominant topic of the retrieved document. In a user study, our explanation method is preferred over regular topic keywords.

{HOTTER}: {H}ierarchical Optimal Topic Transport with Explanatory Context Representations

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment errors by relying mainly on uninformative tokens from the source sequence. However, we observe that NMT models assign attention to these tokens to regulate the contribution in the prediction of the two contexts, the source and the prefix of the target sequence. We provide evidence about the influence of wrong alignments on the model behavior, demonstrating that the encoder-decoder attention mechanism is well suited as an interpretability method for NMT. Finally, based on our analysis, we propose methods that largely reduce the word alignment error rate compared to standard induced alignments from attention weights.

Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions

Supplementary Training on Intermediate Labeled-data Tasks (STILT) is a widely applied technique, which first fine-tunes the pretrained language models on an intermediate task before on the target task of interest.
While STILT is able to further improve the performance of pretrained language models, it is still unclear why and when it works. Previous research shows that those intermediate tasks involving complex inference, such as commonsense reasoning, work especially well for RoBERTa-large. In this paper, we discover that the improvement from an intermediate task could be orthogonal to it containing reasoning or other complex skills --- a simple real-fake discrimination task synthesized by GPT2 can benefit diverse target tasks. We conduct extensive experiments to study the impact of different factors on STILT. These findings suggest rethinking the role of intermediate fine-tuning in the STILT pipeline.

Rethinking Why Intermediate-Task Fine-Tuning Works

Models of language trained on very large corpora have been demonstrated useful for natural language processing. As fixed artifacts, they have become the object of intense study, with many researchers "probing" the extent to which they acquire and readily demonstrate linguistic abstractions, factual and commonsense knowledge, and reasoning abilities. Recent work applied several probes to intermediate training stages to observe the developmental process of a large-scale model (Chiang et al., 2020). Following this effort, we systematically answer a question: for various types of knowledge a language model learns, when during (pre)training are they acquired? Using RoBERTa as a case study, we find: linguistic knowledge is acquired fast, stably, and robustly across domains. Facts and commonsense are slower and more domain-sensitive. Reasoning abilities are, in general, not stably acquired. As new datasets, pretraining protocols, and probes emerge, we believe that probing-across-time analyses can help researchers understand the complex, intermingled learning that these models undergo and guide us toward more efficient approaches that accomplish necessary learning faster.

Probing Across Time: What Does RoBERTa Know and When?

This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained models on text classification tasks with meanings of tokens mismatches, and real-world non-text token sequence classification data, including amino acid, DNA, and music. We find that even on non-text data, the models pre-trained on text converge faster, perform better than the randomly initialized models, and only slightly worse than the models using task-specific knowledge. We also find that the representations of the text and non-text pre-trained models share non-trivial similarities.

Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability

The transformer-based pre-trained language models have been tremendously successful in most of the conventional NLP tasks. But they often struggle in those tasks where numerical understanding is required. Some possible reasons can be the tokenizers and pre-training objectives which are not specifically designed to learn and preserve numeracy. Here we investigate the ability of text-to-text transfer learning model (T5), which has outperformed its predecessors in the conventional NLP tasks, to learn numeracy. We consider four numeracy tasks: numeration, magnitude order prediction, finding minimum and maximum in a series, and sorting. We find that, although T5 models perform reasonably well in the interpolation setting, they struggle considerably in the extrapolation setting across all four tasks.

Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model

Counterfactuals are a valuable means for understanding decisions made by ML systems. However, the counterfactuals generated by the methods currently available for natural language text are either unrealistic or introduce imperceptible changes. We propose CounterfactualGAN: a method that combines a conditional GAN and the embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks. Experimental results show that our method produces perceptibly distinguishable counterfactuals, while outperforming four baseline methods on fidelity and human judgments of naturalness, across multiple datasets and multiple predictive models.

Downloads

Next from EMNLP 2021

Refining BERT Embeddings for Document Hashing via Mutual Information Maximization

Similar lecture

Memory-Based Semantic Parsing

.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 EMNLP 2021

Refining BERT Embeddings for Document Hashing via Mutual Information Maximization

Similar lecture

Memory-Based Semantic Parsing

Downloads