United States

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific trigger word inserted. Previous backdoor attacking methods usually assume that attackers have a certain degree of data knowledge, either the dataset which users would use or proxy datasets for a similar task, for implementing the data poisoning procedure. However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples. Experimental results on sentiment analysis and sentence-pair classification tasks show that our method is more efficient and stealthier. We hope this work can raise the awareness of such a critical security risk hidden in the embedding layers of NLP models. Our code is available at https://github.com/ lancopku/Embedding-Poisoning.

NAACL 2021

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

technical paper

Non-autoregressive encoder-decoder models greatly improve decoding speed over autoregressive models, at the expense of generation quality. To mitigate this, iterative decoding models repeatedly infill or refine the proposal of a non-autoregressive model. However, editing at the level of output sequences limits model flexibility. We instead propose iterative realignment, which by refining latent alignments allows more flexible

Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies.

Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering

A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (NMT) tasks.

Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation

End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the compositionality of cascaded systems simplifies learning and enables sophisticated search capabilities. In this work, we present an end-to-end framework that exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks. These hidden intermediates can be improved using beam search to enhance the overall performance and can also incorporate external models at intermediate stages of the network to re-score or adapt towards out-of-domain data. One instance of the proposed framework is a Multi-Decoder model for speech translation that extracts the searchable hidden intermediates from a speech recognition sub-task. The model demonstrates the aforementioned benefits and outperforms the previous state-of-the-art by around +6 and +3 BLEU on the two test sets of Fisher-CallHome and by around +3 and +4 BLEU on the English-German and English-French test sets of MuST-C.

Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks

Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. To boost the models' performance, various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. However, the inherent disparities between the two modalities necessitate a mutual analysis. In this paper, we propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules. Besides conducting a self-supervised masked language modeling task on the two individual modules using unpaired speech and text, SPLAT aligns representations from the two modules in a shared latent space using a small amount of paired speech and text. Thus, during fine-tuning, the speech module alone can produce representations carrying both acoustic information and contextual semantic knowledge of an input acoustic signal. Experimental results verify the effectiveness of our approach on various SLU tasks. For example, SPLAT improves the previous state-of-the-art performance on the Spoken SQuAD dataset by more than 10%.

SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding

Few-shot learning has drawn researchers' attention to overcome the problem of data scarcity. Recently, large pre-trained language models have shown great performance in few-shot learning for various downstream tasks, such as question answering and machine translation. Nevertheless, little exploration has been made to achieve few-shot learning for the fact-checking task. However, fact-checking is an important problem, especially when the amount of information online is growing exponentially every day. In this paper, we propose a new way of utilizing the powerful transfer learning ability of a language model via a perplexity score. The most notable strength of our methodology lies in its capability in few-shot learning. With only two training samples, our methodology can already outperform the Major Class baseline by more than absolute 10% on the F1-Macro metric across multiple datasets. Through experiments, we empirically verify the plausibility of the rather surprising usage of the perplexity score in the context of fact-checking and highlight the strength of our few-shot methodology by comparing it to strong fine-tuning-based baseline models. Moreover, we construct and publicly release two new fact-checking datasets related to COVID-19.

Towards Few-shot Fact-Checking via Perplexity

Providing a reliable explanation for clinical diagnosis based on the Electronic Medical Record (EMR) is fundamental to the application of Artiﬁcial Intelligence in the medical ﬁeld. Current methods mostly treat the EMR as a text sequence and provide explanations based on a precise medical knowledge base, which is disease-speciﬁc and difﬁcult to obtain for experts in reality. Therefore, we propose a counterfactual multi-granularity graph supporting facts extraction (CMGE) method to extract supporting facts from the irregular EMR itself without external knowledge bases in this paper. Speciﬁcally, we ﬁrst structure the sequence of the EMR into a hierarchical graph network and then obtain the causal relationship between multi-granularity features and diagnosis results through counterfactual intervention on the graph. Features having the strongest causal connection with the results provide interpretive support for the diagnosis. Experimental results on real Chinese EMRs of the lymphedema demonstrate that our method can diagnose four types of EMRs correctly, and can provide accurate supporting facts for the results. More importantly, the results on different diseases demonstrate the robustness of our approach, which represents the potential application in the medical ﬁeld.

Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network

Causal inference is the process of capturing cause-effect relationship among variables.

Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis

Performance of supervised deep learning models rely heavily on large amounts of annotated samples. Manually annotating data is expensive and time consuming. Active learning strategies lets the model choose the examples it wants to learn form, thus reducing data requirement. But they often sample redundant examples.

Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation

Given the diversity of the candidates and complexity of job requirements, and since interviewing is an inherently subjective process, it is an important task to ensure consistent, uniform, efficient and objective interviews that result in high quality recruitment. We propose an interview assistant system to automatically, and in an objective manner, select an optimal set of technical questions (from question banks) personalized for a candidate. This set can help a human interviewer to plan for an upcoming interview of that candidate. We formalize the problem of selecting a set of questions as an integer linear programming problem and use standard solvers to get a solution. We use knowledge graph as background knowledge in this formulation, and derive our objective functions and constraints from it. We use candidate’s resume to personalize the selection of questions. We propose an intrisic evaluation to compare a set of suggested questions with actually asked questions. We also use expert interviewers to comparatively evaluate our approach with a set of reasonable baselines.

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

Downloads

Next from NAACL 2021

Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

Similar lecture

Unsupervised Multi-hop Question Answering by Question Generation

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

.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 NAACL 2021

Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

Similar lecture

Unsupervised Multi-hop Question Answering by Question Generation

Downloads