Extending Word2Vec with domain-specific labels

Choosing a proper representation of textual data is an important part of natural language processing. One option is using Word2Vec embeddings, i.e., dense vectors whose properties can to a degree capture the “meaning” of each word. One of the main disadvantages of Word2Vec is its inability to distinguish between antonyms. Motivated by this deficiency, this paper presents a Word2Vec extension for incorporating domain-specific labels. The goal is to improve the ability to differentiate between embeddings of words associated with different document labels or classes. This improvement is demonstrated on word embeddings derived from tweets related to a publicly traded company. Each tweet is given a label depending on whether its publication coincides with a stock price increase or decrease. The extended Word2Vec model then takes this label into account. The user can also set the weight of this label in the embedding creation process. Experiment results show that increasing this weight leads to a gradual decrease in cosine similarity between embeddings of words associated with different labels. This decrease in similarity can be interpreted as an improvement of the ability to distinguish between these words.

---

1. This paper was supported by the SGS project No. SP2022/113. This support is gratefully acknowledged.

---

2. Short article

---

3. Track 1: 17th International Symposium on Advanced Artificial Intelligence in Applications

---

4. Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).