An official website of the United States government
Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be interpreted via compositional operations such as sentence fusion or difference. It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space. To more effectively bridge the continuous embedding and discrete text spaces, we explore the plausibility of incorporating various compositional properties into the sentence embedding space that allows us to interpret embedding transformations as compositional sentence operations. We propose InterSent, an end-to-end framework for learning interpretable sentence embeddings that supports compositional sentence operations in the embedding space. Our method optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddings. Experimental results demonstrate that our method significantly improves the interpretability of sentence embeddings on four textual generation tasks over existing approaches while maintaining strong performance on traditional semantic similarity tasks.
more »
« less
Semantic Oppositeness Embedding Using an Autoencoder-Based Learning Model
Semantic oppositeness is the natural counterpart of the much popular natural language processing concept, semantic similarity. Much like how semantic similarity is a measure of the degree to which two concepts are similar, semantic oppositeness yields the degree to which two concepts would oppose each other. This complementary nature has resulted in most applications and studies incorrectly assuming semantic oppositeness to be the inverse of semantic similarity. In other trivializations, “semantic oppositeness” is used interchangeably with “antonymy”, which is as inaccurate as replacing semantic similarity with simple synonymy. These erroneous assumptions and over-simplifications exist due, mainly, to either lack of information, or the computational complexity of calculation of semantic oppositeness. The objective of this research is to prove that it is possible to extend the idea of word vector embedding to incorporate semantic oppositeness, so that an effective mapping of semantic oppositeness can be obtained in a given vector space. In the experiments we present in this paper, we show that our proposed method achieves a training accuracy of 97.91% and a test accuracy of 97.82%, proving the applicability of this method even in potentially highly sensitive applications and dispelling doubts of over-fitting. Further, this work also introduces a novel, unanchored vector embedding method and a novel, inductive transfer learning process.
more »
« less
- Award ID(s):
- 1747798
- PAR ID:
- 10131162
- Date Published:
- Journal Name:
- Proceedings of the 30th International Conference on Database and Expert Systems Applications
- Page Range / eLocation ID:
- 159-174
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
ord embeddings are commonly used to measure word-level semantic similarity in text, especially in direct word- to-word comparisons. However, the relationships between words in the embedding space are often viewed as approximately linear and concepts comprised of multiple words are a sort of linear combination. In this paper, we demonstrate that this is not generally true and show how the relationships can be better captured by leveraging the topology of the embedding space. We propose a technique for directly computing new vectors representing multiple words in a way that naturally combines them into a new, more consistent space where distance better correlates to similarity. We show that this technique works well for natural language, even when it comprises multiple words, on a simple task derived from WordNet synset descriptions and examples of words. Thus, the generated vectors better represent complex concepts in the word embedding space.more » « less
-
Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown particular strength in improving the performance of modestly sized LLMs, sometimes inducing performance competitive with much larger model variants. In this paper, we ask two questions: (1) How sensitive are instruction-tuned models to the particular phrasings of instructions, and, (2) How can we make them more robust to such natural language variation? To answer the former, we collect a set of 319 instructions manually written by NLP practitioners for over 80 unique tasks included in widely used benchmarks, and we evaluate the variance and average performance of these instructions as compared to instruction phrasings observed during instruction fine-tuning. We find that using novel (unobserved) but appropriate instruction phrasings consistently degrades model performance, sometimes substantially so. Further, such natural instructions yield a wide variance in downstream performance, despite their semantic equivalence. Put another way, instruction-tuned models are not especially robust to instruction re-phrasings. We propose a simple method to mitigate this issue by introducing soft prompt'' embedding parameters and optimizing these to maximize the similarity between representations of semantically equivalent instructions. We show that this method consistently improves the robustness of instruction-tuned models.more » « less
-
null (Ed.)This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode language structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines.more » « less
-
This paper focuses on a newly challenging setting in hard-label adversarial attacks on text data by taking the budget information into account. Although existing approaches can successfully generate adversarial examples in the hard-label setting, they follow an ideal assumption that the victim model does not restrict the number of queries. However, in real-world applications the query budget is usually tight or limited. Moreover, existing hard-label adversarial attack techniques use the genetic algorithm to optimize discrete text data by maintaining a number of adversarial candidates during optimization, which can lead to the problem of generating low-quality adversarial examples in the tight-budget setting. To solve this problem, in this paper, we propose a new method named TextHoaxer by formulating the budgeted hard-label adversarial attack task on text data as a gradient-based optimization problem of perturbation matrix in the continuous word embedding space. Compared with the genetic algorithm-based optimization, our solution only uses a single initialized adversarial example as the adversarial candidate for optimization, which significantly reduces the number of queries. The optimization is guided by a new objective function consisting of three terms, i.e., semantic similarity term, pair-wise perturbation constraint, and sparsity constraint. Semantic similarity term and pair-wise perturbation constraint can ensure the high semantic similarity of adversarial examples from both comprehensive text-level and individual word-level, while the sparsity constraint explicitly restricts the number of perturbed words, which is also helpful for enhancing the quality of generated text. We conduct extensive experiments on eight text datasets against three representative natural language models, and experimental results show that TextHoaxer can generate high-quality adversarial examples with higher semantic similarity and lower perturbation rate under the tight-budget setting.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-27615-7_12
